DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Rejections - 35 USC § 112 The following is a quotation of 35 U.S.C. 112(b): (b ) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the appl icant regards as his invention. Claim s 2 - 10, 13 - 1 7 and 19-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim s 2 , 7 , 9 , 13 , 16 and 19-20 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being incomplete for omitting essential elements, such omission amounting to a gap between the elements. See MPEP § 2172.01. The omitted elements are not defining the variables y i and x i in claims 2 , 13 and 19 . The omitted element is not defining the function f in claims 9 and 16 . And the omitted elements are not defining the variable G U in claims 7 , 15 , and 20 . These omissions make the claim limitations indefinite since one of ordinary skill in the art would not be able to infer how these variables /functions relat e and/or transform the expressions claimed . Claim Rejections - 35 USC § 102 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis ( i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale , or otherwise available to the public before the effective filing date of the claimed invention. (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. Claims 1-7 and 9-10 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Bihani ,et al. "StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes." arXiv preprint arXiv:2301.12477 v1 ( 01/29/ 2023) (“ Bihani ”) Regarding claim 1 , Bihani teaches a system comprising: a processor; and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor ( Bihani , pg., 7, “ Software packages: numpy-1.24.1, jax-0.4.1, jax-md-0.2.24, jaxlib-0.4.1, jraph-0.0.6.dev0, flax-0.6.3, optax-0.1.4 Hardware: Processor: 2x E5-2680 v3 @2.5GHz/12-Core ‘ Haswell ’ CPU RAM: 62 GB [ a processor; and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor ] ’ " ) , cause the processor to: i) dope a crystal graph for a crystalline material with dopant atoms ( Bihani , pgs., 4-5, see also fig. 2, “ Given an atomic structure represented as a graph G with the potential energy U g our goal is to update the positions of the nodes v∈V for t steps...[t] he action corresponds to displacing each of the nodes (atoms) in all d directions as determined by policy π [ i) dope a crystal graph for a crystalline material with dopant atoms ] . ” ) ; ii) determine a state of the doped crystal graph ( Bihani , pgs., 4-5, see also fig. 2, “ We denote the state of a graph G at step t as a matrix S G t [ ii) determine a state of the doped crystal graph ] ... [i] ntuitively, the state should contain information that would help our model make a decision regarding the magnitude and direction of each node’s displacement . ” ) ; iii) move at least one of the dopant atoms along an edge of the crystal graph per a doping policy ( Bihani , pg., 6, see also fig. 2, “ As discussed, at each step t , the nodes in G t are displaced based upon the action determined by policy function [ iii) move at least one of the dopant atoms along an edge of the crystal graph per a doping policy ] ...[f]or an action a i ∈ R d on node i , we define the policy [as] π θ ( a i | S G t ) ... [f] or a trajectory of length T , we sample actions for all nodes of the graph at each step t using policy π . ” ) ; iv) determine another state of the doped crystal graph and a reward accumulation of moving the at least one dopant atoms ( Bihani , pgs., 4-5, see also fig. 2, “ [W] e use discounted rewards D t to increase the probability of actions that lead to higher rewards in the long term. The discounted rewards are computed as the sum of the rewards over a trajectory of actions with varying degrees of importance (short-term and long-term ) [ and a reward accumulation of moving the at least one dopant atoms ] ... [a] t each step t, all the nodes in the grap h G t are displaced based on the translation determined by the policy function π . The graph state thus transits from S G t to S G t+1 [ iv) determine another state of the doped crystal graph ] . ” ) ; v) update the doping policy; and repeat steps iii - v for a predetermined number of cycles ( Bihani , pgs., 6-7 , see also fig. 2, “ Towards this, we use REINFORCE gradient estimator with baseline ... to optimize the parameters of our policy network. Specifically, we wish to maximize the reward obtained for the trajectory of length T with discounted reward s D t . To this end, we define a reward function J( π θ ) ...[ w]e then, optimize J( π θ ) with a baseline b [ v) update the doping policy; ] .... [f] or a given set of training graphs, we optimize the parameters of the policy network ...for T steps [ and repeat steps iii - v for a predetermined number of cycles ] .... ” ) . Regarding claim 2 , Bihani teaches t he system according to claim 1, wherein the crystal graph for the crystalline material is defined by the expression: G={V, E} where V=[ y i , x i , i=1,…,N]} is a set of nodes in the crystal graph ; and where E={ e i,j |i,j∈{1,…,N}} is a set of edges representing bonds in the crystal graph ( Bihani , pgs., 3-4, see also fig. 2, “ Each x i represents the position of th e i th atom in a d-dimensional space... an atomic system is represented by a graph G=( V , E ) [ wherein the crystal graph for the crystalline material is defined by the expression: G={V, E} ] where the nodes v∈ V denotes the atoms [ where V=[ y i , x i , i=1,…,N]} is a set of nodes in the crystal graph ] and e vu ∈E represents edges corresponding to the interactions between atoms v and u [ and where E= { e i,j |i,j∈{1,…,N}} is a set of edges representing bonds in the crystal graph ] . .. the edges are defined ... as a function of the distance between two nodes as E ={ e uv =(u, v)|d u, v ≤δ} ” ) . Regarding claim 3 , Bihani teaches t he system according to claim 2, wherein the state of the doped crystal includes calculating states of the dopant atoms after movement of the at least one of the dopant atoms along at least one edge of the crystal ( Bihani , pg., 5, see also fig. 2, “A t each step t, all the nodes in the graph G t are displaced based on the translation determined by the policy function π . The graph state thus transits from S G t to S G t+1 [ includes calculating states of the dopant atoms after movement of the at least one of the dopant atoms along at least one edge of the crystal ] . ” ) . Regarding claim 4 , Bihani teaches t he system according to claim 3, wherein the state of the dopant atoms is defined as the crystal graph with the dopant atoms: G D =( V D , E) where V D is the set of nodes that contain dopants ( Bihani , pgs., 3-4, “A n atomic system is represented by a graph G=(V, E) where the nodes v∈ V denotes the atoms [ is defined as the crystal graph with the dopant atoms: G D =( V D , E) where V D is the set of nodes that contain dopants ] and e vu ∈E represents edges corresponding to the interactions between atoms v and u .” ) . Regarding claim 5 , Bihani teaches t he system according to claim 3, wherein the dopant atoms are moved between nearest neighbor nodes of the crystal graph ( Bihani , pgs., 4-6, see also fig. 2, “[T] he neighborhood of a node v given by N v ={u| u,v ∈E} ... [t] he atoms in a system interact with other atoms in their neighborhood [ between nearest neighbor nodes of the crystal graph ] ... [t] o generate the embedding for node v at layer l+1 we perform the following transformation [in equation 6]... h vu l is the embedding of the edge between node v and u and u∈ N v [ wherein the dopant atoms are moved ] ” ) . Regarding claim 6 , Bihani teaches t he system according to claim 3, wherein the nearest neighbor nodes of the crystal graph are connected with an edge of the crystal graph ( Bihani , pgs., 3-4, see also fig. 2, “ the edges are defined... as a function of the distance between two nodes as E={ e uv =(u, v)|d u, v ≤δ} where d(u, v) is a distance function over node positions and δ is a distance threshold. This threshold can be selected based on the first neighbor cutoff of the atomic structures as obtained from the pair-distribution function ...[t] he cutoff thus defines the neighborhood of a node v given by N v ={u| u,v ∈E} [ wherein the nearest neighbor nodes of the crystal graph are connected with an edge of the crystal graph ] . ” ) . Regarding claim 7 , Bihani teaches t he system according to claim 5, wherein the movement of the dopant atoms along the edge of the crystal is defined as: a ij G U ={set y j = y D , y i = y i D , if j∈ N i, y D } where y D is the atom type of the dopant , y i U is the atom type of site j, and N i, y D is the space of all permitted destination nodes ( Bihani , pg., 3, “ The configuration Ω c ( x 1 , x 2 ,… x N ) of an atomic system is given by the positions of all the atoms in the system [ a ij G U ={set y j = y D , y i = y i D , if j∈ N i, y D } ] ...their types ω i [ where y D is the atom type of the dopant ] . Each x i represents the position of the i th atom in a d -dimensional space where d is typically 2 or 3 [ y i U is the atom type of site j, ] . The potential energy U of an N -atom structure is a function of Ω c ... [s] tarting from Ω c , our goal is to obtain the configuration Ω min exhibiting the minimum energy U Ω min by displacing the atoms [ and N i, y D is the space of all permitted destination nodes ] . ” ) . Regarding claim 9 , Bihani teaches t he system according to claim 1, wherein a reward for the reward accumulation is defined by: r t =f( G t , G t-1 ) where r t , is the reward at step t , G t is the state of the crystal graph at step t, and G t-1 is the state of the crystal graph at step t-1 ( Bihani , pg., 5, “ One option is to define the reward R t at step t ≥ 0 as the reduction in potential energy of the system at step t, i.e., U G t - U G t+1 . ” ) . Regarding claim 10 , Bihani teaches t he system according to claim 9, wherein the reward is a function of a property of the doped crystal graph selected from the group consisting of a formation energy , a catalytic activity, an electronic band gap, an elastic modulus, and an electrical conductivity ( Bihani , pg., 3, “The configuration Ω c ( x 1 , x 2 ,… x N ) of an atomic system is given by the positions of all the atoms in the system...their types ω i ...[t] he potential energy U of an N -atom structure is a function of Ω c ... [s]tarting from Ω c , our goal is to obtain the configuration Ω min exhibiting the minimum energy U Ω min by displacing the atoms [ formation energy ] . ” ) . Claim Rejections - 35 USC § 103 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis ( i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claim s 8 and 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bihani,et al. "StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes." arXiv preprint arXiv:2301.12477v1 (01/29/2023)(“ Bihani ”) in view of Banik et al., A Continuous Action Space Tree search for INverse desiGn (CASTING) Framework for Materials Discovery. arXiv preprint arXiv:2212.12106. 2022 Dec 23 (“ Banik ”) . Regarding claim 8 , Bihani teaches t he system according to claim 5, but does not teach : wherein the state of the dopant atoms and the movement of the dopant atoms are a function of a number of the dopant atoms inserted into the crystal graph and are independent of a size of unit cell of the crystal graph . However, Banik teaches: wherein the state of the dopant atoms and the movement of the dopant atoms are a function of a number of the dopant atoms inserted into the crystal graph and are independent of a size of unit cell of the crystal graph ( Banik , pg., 5, see also fig s . 2 and 4(c) , “[A] ny crystal structure is represented as a vector with 6 lattice parameters, and 3 times the number of atom coordinates (x, y, z) with chemical species belonging to each point [ wherein the state of the dopant atoms and the movement of the dopant atoms ] . MCTS spawns a tree with each node containing a point in the parameter space being searched for and a score indicating the potential to find a promising structure nearby ... [m] ainly 4 types of perturbation (Fig. 2 (c)) moves were used (a) ‘ Add ato m’ (retaining the composition) [ function of a number of the dopant atoms inserted into the crystal graph and are independent of a size of unit cell of the crystal graph ] ...” ) It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Bihani with the teachings of Banik the motivation to do so would be to use reinforcement learning as a search technique to find a tractable solution when it comes to the problem of optimiz ing crystalline structures to have certain properties( Banik , pg., 1, abstract, “ Fast and accurate prediction of optimal crystal structure, topology, and microstructures is important for accelerating the design and discovery of new materials for energy applications ... [a] challenge lies in the exorbitantly large structural and compositional space presented by the various elements and their combinations ... we introduce CASTING, which is an RL-based scalable framework for crystal structure, topology, and potentially microstructure prediction. CASTING employs an RL-based continuous search space decision tree (MCTS -Monte Carlo Tree Search) algorithm with ... important modifications (i) a modified rewards scheme for improved search space exploration ... and (iii) adaptive sampling during playouts for efficient and scalable search . ”) . Regarding claim 11 , Bihani teaches t he system according to claim 1, wherein the machine-readable instructions, when executed by the processor, cause the processor to ( Bihani , pg., 7, “ Software packages: numpy-1.24.1, jax-0.4.1, jax-md-0.2.24, jaxlib-0.4.1, jraph- 0.0.6.dev0, flax-0.6.3, optax-0.1.4 Hardware: Processor: 2x E5-2680 v3 @2.5GHz/12-Core ‘ Haswell ’ CPU RAM: 62 GB ’ " ) . Bihani does not teach : prevent the dopant atoms from moving along predefined edges of the crystal graph. However, Banik teaches: prevent the dopant atoms from moving along predefined edges of the crystal graph ( Banik , pg., 25, see also fig. 10, “ We define a uniqueness function on the exploration side of the node selection rule to avoid degeneracies in the search space. For situations where we simply wish to limit two branches from approaching the same minima, we found a simple definition [as detailed in equation (1)] [ prevent the dopant atoms from moving along predefined edges of the crystal graph ] .... ” ) It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Bihani with the teachings of Banik the motivation to do so would be to use reinforcement learning as a search technique to find a tractable solution when it comes to the problem of optimizing crystalline structures to have certain properties( Banik , pg., 1, abstract, “Fast and accurate prediction of optimal crystal structure, topology, and microstructures is important for accelerating the design and discovery of new materials for energy applications... [a] challenge lies in the exorbitantly large structural and compositional space presented by the various elements and their combinations... we introduce CASTING, which is an RL-based scalable framework for crystal structure, topology, and potentially microstructure prediction. CASTING employs an RL-based continuous search space decision tree (MCTS -Monte Carlo Tree Search) algorithm with...important modifications (i) a modified rewards scheme for improved search space exploration...and (iii) adaptive sampling during playouts for efficient and scalable search.”). Regarding claim 12 , Bihani teaches a method comprising: i) reading a crystal graph for an inorganic material and a doping policy for doping the inorganic material from a memory communicably coupled to and using a processor ( Bihani , pgs., 7-8, “Software packages: numpy-1.24.1, jax-0.4.1, jax-md-0.2.24, jaxlib-0.4.1, jraph-0.0.6.dev0, flax-0.6.3, optax-0.1.4 Hardware: Processor: 2x E5-2680 v3 @2.5GHz/12-Core ‘Haswell’ CPU RAM: 62 GB . To evaluate the performance of STRIDERNET, we consider three systems that ar e characterized by rough energy landscape, namely, (i) binary LJ mixture, (ii) Stillinger-Weber (SW) silicon, and (iii) calcium-silicate-hydrate (C-S-H) gel [ i) reading a crystal graph for an inorganic material and a doping policy for doping the inorganic material ] . ” ) ; [ ii) inserting dopant atoms at a first set of atom sites ] in the crystal graph ( Bihani , pgs., 3-4, see also fig. 2, “ Each x i represents the position of th e i th atom in a d-dimensional space... an atomic system is represented by a graph G=(V, E) where the nodes v∈ V denotes the atoms and e vu ∈E represents edges corresponding to the interactions between atoms v and u ... the edges are defined ... as a function of the distance between two nodes as E ={ e uv =(u, v)|d u, v ≤δ} ) ; iii) calculating a state of the dopant atoms ( Bihani , pgs., 4-5, see also fig. 2, “ We denote the state of a graph G at step t as a matrix S G t ... [i] ntuitively, the state should contain information that would help our model make a decision regarding the magnitude and direction of each node’s displacement . ” ) ; iv) moving the dopant atoms along at least one edge of the crystal graph to a subsequent set atom sites in the crystal graph ( Bihani , pg., 6, see also fig. 2, “ As discussed, at each step t , the nodes in G t are displaced based upon the action determined by policy function ...[f]or an action a i ∈ R d on node i , we define the policy [as] π θ ( a i | S G t ) ... [f] or a trajectory of length T , we sample actions for all nodes of the graph at each step t using policy π . ” ) ; v) calculating a subsequent state of the dopant atoms and a reward of moving the dopant atoms along the at least one edge of the crystal graph ( Bihani , pgs., 4-5, see also fig. 2, “[W] e use discounted rewards D t to increase the probability of actions that lead to higher rewards in the long term. The discounted rewards are computed as the sum of the rewards over a trajectory of actions with varying degrees of importance (short-term and long-term) ... [a] t each step t, all the nodes in the grap h G t are displaced based on the translation determined by the policy function π . The graph state thus transits from S G t to S G t+1 . ” ) ; vi) updating the doping policy; vii) repeating steps iv-vi for a predetermine number of cycles such that a learned doping policy is provided ( Bihani , pgs., 6-7, see also fig. 2, “Towards this, we use REINFORCE gradient estimator with baseline... to optimize the parameters of our policy network. Specifically, we wish to maximize the reward obtained for the trajectory of length T with discounted rewards D t . To this end, we define a reward function J( π θ ) ...[w]e then, optimize J( π θ ) with a baseline b .... [f]or a given set of training graphs, we optimize the parameters of the policy network...for T steps....” ) ; and viii) inferencing a doped crystalline material using the learned doping policy ( Bihani , pg., 7, “ For a given set of training graphs, we optimize the parameters of the policy network π θ for T steps using Eq. 10 . Once we obtain the trained model π θ , we adapt it to a target graph G target , which was unseen during training. ” ) . While Bihani does teach the crystal graph Bihani does not teach: ii) inserting dopant atoms at a first set of atom sites . However, Banik teaches: ii) inserting dopant atoms at a first set of atom sites ( Banik , pg., 5, see also figs. 2 and 4(c), “[A] ny crystal structure is represented as a vector with 6 lattice parameters, and 3 times the number of atom coordinates (x, y, z) with chemical species belonging to each point. MCTS spawns a tree with each node containing a point in the parameter space being searched for and a score indicating the potential to find a promising structure nearby ... 4 types of perturbation (Fig. 2 (c)) moves were used (a) ‘ Add ato m’ (retaining the composition) ...” ) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Bihani with the teachings of Banik the motivation to do so would be to use reinforcement learning as a search technique to find a tractable solution when it comes to the problem of optimizing crystalline structures to have certain properties( Banik , pg., 1, abstract, “ Fast and accurate prediction of optimal crystal structure, topology, and microstructures is important for accelerating the design and discovery of new materials for energy applications ... [a] challenge lies in the exorbitantly large structural and compositional space presented by the various elements and their combinations ... we introduce CASTING, which is an RL-based scalable framework for crystal structure, topology, and potentially microstructure prediction. CASTING employs an RL-based continuous search space decision tree (MCTS -Monte Carlo Tree Search) algorithm with ... important modifications (i) a modified rewards scheme for improved search space exploration ... and (iii) adaptive sampling during playouts for efficient and scalable search .”). Referring to dependent claims 13-17, they are rejected on the same basis as dependent claims 2, 4, 7, and 9-10 since they are analogous claims. Regarding claim 18 , Bihani in view of Banik teaches t he method according to claim 12 further comprising calculating an optimized doped crystalline material using the learned doping policy ( Bihani , pgs. 9-11, see also table 2, “ Table 2 shows the performance of STRIDERNET on all the system sizes. Interestingly for all structures from 25 to 500 atoms, we observe that STRIDERNET gives the best performance in terms of both the overall minimum and the mean of the minimum energies of 10 structures ” ) . Regarding claim 19 , Bihani teaches a system comprising: a processor; and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to ( Bihani , pgs., 7-8, “Software packages: numpy-1.24.1, jax-0.4.1, jax-md-0.2.24, jaxlib-0.4.1, jraph-0.0.6.dev0, flax-0.6.3, optax-0.1.4 Hardware: Processor: 2x E5-2680 v3 @2.5GHz/12-Core ‘Haswell’ CPU RAM: 62 GB .” ); i) read a crystal graph for a crystalline material and a doping policy for doping the crystalline material ( Bihani , pgs., 7-8, “ To evaluate the performance of STRIDERNET, we consider three systems that ar e characterized by rough energy landscape, namely, (i) binary LJ mixture, (ii) Stillinger-Weber (SW) silicon, and (iii) calcium-silicate-hydrate (C-S-H) gel. ” ), the crystal graph defined by the expression : G={V, E} where V=[ y i , x i , i=1,…,N]} is a set of nodes in the crystal graph; and where E={ e i,j |i,j∈{1,…,N}} is a set of edges representing bonds in the crystal graph ( Bihani , pgs., 3-4, see also fig. 2, “ Each x i represents the position of th e i th atom in a d-dimensional space... an atomic system is represented by a graph G=(V, E) where the nodes v∈ V denotes the atoms and e vu ∈E represents edges corresponding to the interactions between atoms v and u ... the edges are defined ... as a function of the distance between two nodes as E ={ e uv =(u, v)|d u, v ≤δ} ” ) [ ii) insert dopant atoms ] in the crystal graph ( Bihani , pgs., 3-4, see also fig. 2, “ Each x i represents the position of th e i th atom in a d-dimensional space... an atomic system is represented by a graph G=(V, E) where the nodes v∈ V denotes the atoms and e vu ∈E represents edges corresponding to the interactions between atoms v and u ... the edges are defined ... as a function of the distance between two nodes as E ={ e uv =(u, v)|d u, v ≤δ} ) ; iii) determine a state of the dopant atoms ( Bihani , pgs., 4-5, see also fig. 2, “ We denote the state of a graph G at step t as a matrix S G t ... [i] ntuitively, the state should contain information that would help our model make a decision regarding the magnitude and direction of each node’s displacement . ” ) ; iv) move at least one of the dopant atoms along an edge of the crystal graph per the doping policy ( Bihani , pg., 6, see also fig. 2, “ As discussed, at each step t , the nodes in G t are displaced based upon the action determined by policy function ...[f]or an action a i ∈ R d on node i , we define the policy [as] π θ ( a i | S G t ) ... [f] or a trajectory of length T , we sample actions for all nodes of the graph at each step t using policy π . ” ) ; v) determine another state and an accumulated reward of moving the dopant moved along the edge ( Bihani , pgs., 4-5, see also fig. 2, “[W] e use discounted rewards D t to increase the probability of actions that lead to higher rewards in the long term. The discounted rewards are computed as the sum of the rewards over a trajectory of actions with varying degrees of importance (short-term and long-term) ... [a] t each step t, all the nodes in the grap h G t are displaced based on the translation determined by the policy function π . The graph state thus transits from S G t to S G t+1 . ” ) ; vi) update the doping policy; and vii). repeat steps iv - vi until a predefined number of steps are completed such that a learned doping policy is provided ( Bihani , pgs., 6-7, see also fig. 2, “Towards this, we use REINFORCE gradient estimator with baseline... to optimize the parameters of our policy network. Specifically, we wish to maximize the reward obtained for the trajectory of length T with discounted rewards D t . To this end, we define a reward function J( π θ ) ...[w]e then, optimize J( π θ ) with a baseline b .... [f]or a given set of training graphs, we optimize the parameters of the policy network...for T steps....” ) ; and viii) inference a doped crystalline material using the learned doping policy ( Bihani , pg., 7, “ For a given set of training graphs, we optimize the parameters of the policy network π θ for T steps using Eq. 10. Once we obtain the trained model π θ , we adapt it to a target graph G target , which was unseen during training. ” ) . While Bihani does teach the crystal graph Bihani does not teach: ii) insert dopant atoms . However, Banik teaches: ii) insert dopant atoms ( Banik , pg., 5, see also figs. 2 and 4(c), “[A] ny crystal structure is represented as a vector with 6 lattice parameters, and 3 times the number of atom coordinates (x, y, z) with chemical species belonging to each point. MCTS spawns a tree with each node containing a point in the parameter space being searched for and a score indicating the potential to find a promising structure nearby ... 4 types of perturbation (Fig. 2 (c)) moves were used (a) ‘ Add ato m’ (retaining the composition) ...” ). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Bihani with the teachings of Banik the motivation to do so would be to use reinforcement learning as a search technique to find a tractable solution when it comes to the problem of optimizing crystalline structures to have certain properties( Banik , pg., 1, abstract, “ Fast and accurate prediction of optimal crystal structure, topology, and microstructures is important for accelerating the design and discovery of new materials for energy applications ... [a] challenge lies in the exorbitantly large structural and compositional space presented by the various elements and their combinations ... we introduce CASTING, which is an RL-based scalable framework for crystal structure, topology, and potentially microstructure prediction. CASTING employs an RL-based continuous search space decision tree (MCTS -Monte Carlo Tree Search) algorithm with ... important modifications (i) a modified rewards scheme for improved search space exploration ... and (iii) adaptive sampling during playouts for efficient and scalable search .”). Regarding claim 20 , Bihani in view of Banik teaches t he system according to claim 19, where the state of the dopant atoms is defined as the crystal graph with dopant: G D =( V D , E) where V D is the set of nodes that contain dopants ( Bihani , pgs., 3-4, “A n atomic system is represented by a graph G=(V, E) where the nodes v∈ V denotes the atoms and e vu ∈E represents edges corresponding to the interactions between atoms v and u .” ) , and the move of the dopant atoms along the edge of the crystal graph is defined as : a ij G U ={set y j = y D , y i = y i D , if j∈ N i, y D } where y D is the atom type of the dopant, y i U is the atom type of site j, and N i, y D is the space of all permitted destination nodes( Bihani , pg., 3, “The configuration Ω c ( x 1 , x 2 ,… x N ) of an atomic system is given by the positions of all the atoms in the system...their types ω i . Each x i represents the position of the i th atom in a d -dimensional space where d is typically 2 or 3. The potential energy U of an N -atom structure is a function of Ω c ... [s]tarting from Ω c , our goal is to obtain the configuration Ω min exhibiting the minimum energy U Ω min by displacing the atoms. ” ) . Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. H agawa et al. US 2021/0133635 Al ( details a material descriptor generation method in which a base material is doped using a neural network architecture ) Any inquiry concerning this communication or earlier communications from the examiner should be directed to FILLIN "Examiner name" \* MERGEFORMAT ADAM C STANDKE whose telephone number is FILLIN "Phone number" \* MERGEFORMAT (571)270-1806 . The examiner can normally be reached FILLIN "Work Schedule?" \* MERGEFORMAT Gen. M-F 9-9PM EST . Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, FILLIN "SPE Name?" \* MERGEFORMAT Michael J Huntley can be reached at FILLIN "SPE Phone?" \* MERGEFORMAT (303) 297-4307 . The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. FILLIN "Examiner Stamp" \* MERGEFORMAT /Adam C Standke/ Primary Examiner Art Unit 2129