{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning/papers/84","list_of":"/task/reinforcement-learning","task":"Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":84,"pages_in_order":132,"rows_per_page":100,"rows":[8301,8400],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning","prev":"/task/reinforcement-learning/papers/83","next":"/task/reinforcement-learning/papers/85","papers":[{"url":null,"slug":"gradient-free-neural-network-training-via","title":"Gradient-Free Neural Network Training via Synaptic-Level Reinforcement Learning","date":"2021-05-29","arxiv_id":"2105.14383","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-theory-of-reinforcement-learning-with","title":"On the Theory of Reinforcement Learning with Once-per-Episode Feedback","date":"2021-05-29","arxiv_id":"2105.14363","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-approximate-and-exact-numeral","title":"Learning Approximate and Exact Numeral Systems via Reinforcement Learning","date":"2021-05-28","arxiv_id":"2105.13857","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-on-line-sequence","title":"Reinforcement Learning for on-line Sequence Transformation","date":"2021-05-28","arxiv_id":"2105.14097","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-aware-transfer-in-reinforcement-learning","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","date":"2021-05-28","arxiv_id":"2105.14127","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-intervention-for-causal-inference","title":"Stochastic Intervention for Causal Inference via Reinforcement Learning","date":"2021-05-28","arxiv_id":"2105.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-guided-inverse-reinforcement-learning","title":"Task-Guided Inverse Reinforcement Learning Under Partial Information","date":"2021-05-28","arxiv_id":"2105.14073","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-deep-reinforcement-learning","title":"Transferable Deep Reinforcement Learning Framework for Autonomous Vehicles with Joint Radar-Data Communications","date":"2021-05-28","arxiv_id":"2105.13670","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-reinforcement-learning-by-forward","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","date":"2021-05-27","arxiv_id":"2105.12991","repositories_listed":0,"syntology":null},{"url":null,"slug":"pattern-transfer-learning-for-reinforcement","title":"Pattern Transfer Learning for Reinforcement Learning in Order Dispatching","date":"2021-05-27","arxiv_id":"2105.13218","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generalised-inverse-reinforcement-learning","title":"A Generalised Inverse Reinforcement Learning Framework","date":"2021-05-25","arxiv_id":"2105.11812","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-nonparametric-reinforcement-learning","title":"Bayesian Nonparametric Reinforcement Learning in LTE and Wi-Fi Coexistence","date":"2021-05-25","arxiv_id":"2105.12249","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-uav-collision-avoidance-using","title":"Interpretable UAV Collision Avoidance using Deep Reinforcement Learning","date":"2021-05-25","arxiv_id":"2105.12254","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowsr-knowledge-sharing-among-homogeneous","title":"KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning","date":"2021-05-25","arxiv_id":"2105.11611","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-modeling-via-random-utility","title":"Trajectory Modeling via Random Utility Inverse Reinforcement Learning","date":"2021-05-25","arxiv_id":"2105.12092","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-and-curriculum-learning-in","title":"Transfer Learning and Curriculum Learning in Sokoban","date":"2021-05-25","arxiv_id":"2105.11702","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-asymmetric-actor-critic-for","title":"Unbiased Asymmetric Reinforcement Learning under Partial Observability","date":"2021-05-25","arxiv_id":"2105.11674","repositories_listed":0,"syntology":null},{"url":null,"slug":"room-clearance-with-feudal-hierarchical","title":"Room Clearance with Feudal Hierarchical Reinforcement Learning","date":"2021-05-24","arxiv_id":"2105.11328","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-reinforcement-learning-for","title":"Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication","date":"2021-05-22","arxiv_id":"2105.10716","repositories_listed":0,"syntology":null},{"url":null,"slug":"de-biased-modelling-of-search-click-behavior","title":"De-Biased Modelling of Search Click Behavior with Reinforcement Learning","date":"2021-05-21","arxiv_id":"2105.10072","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-fast","title":"Meta Reinforcement Learning for Fast Adaptation of Hierarchical Policies","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-disease-1","title":"Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-instance","title":"Reinforcement learning for instance segmentation with high-level priors","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-design-choices-in-offline-model-1","title":"Revisiting Design Choices in Offline Model Based Reinforcement Learning","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rlirank-learning-to-rank-with-reinforcement","title":"RLIRank: Learning to Rank with Reinforcement Learning for Dynamic Search","date":"2021-05-21","arxiv_id":"2105.10124","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-stochastic-composite-augmented-lagrangian","title":"A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning","date":"2021-05-20","arxiv_id":"2105.09716","repositories_listed":0,"syntology":null},{"url":null,"slug":"objective-aware-traffic-simulation-via","title":"Objective-aware Traffic Simulation via Inverse Reinforcement Learning","date":"2021-05-20","arxiv_id":"2105.09560","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-sample-efficient-reinforcement","title":"Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics","date":"2021-05-20","arxiv_id":"2105.09719","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-conversational-recommendation-policy","title":"Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning","date":"2021-05-20","arxiv_id":"2105.09710","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-abac-policy-learning-a-reinforcement","title":"Adaptive ABAC Policy Learning: A Reinforcement Learning Approach","date":"2021-05-18","arxiv_id":"2105.08587","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-deep-reinforcement-learning","title":"Application of deep reinforcement learning for Indian stock trading automation","date":"2021-05-18","arxiv_id":"2106.16088","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-information-in-stochastic","title":"Learning and Information in Stochastic Networks and Queues","date":"2021-05-18","arxiv_id":"2105.08769","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-multimodal-transportation-planning","title":"Online Multimodal Transportation Planning using Deep Reinforcement Learning","date":"2021-05-18","arxiv_id":"2105.08374","repositories_listed":0,"syntology":null},{"url":null,"slug":"pobrl-optimizing-multi-document-summarization","title":"PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies","date":"2021-05-18","arxiv_id":"2105.08244","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-adaptive-video","title":"Reinforcement Learning for Adaptive Video Compressive Sensing","date":"2021-05-18","arxiv_id":"2105.08205","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsity-prior-regularized-q-learning-for","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","date":"2021-05-18","arxiv_id":"2105.08666","repositories_listed":0,"syntology":null},{"url":null,"slug":"sublinear-least-squares-value-iteration-via","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","date":"2021-05-18","arxiv_id":"2105.08285","repositories_listed":0,"syntology":null},{"url":null,"slug":"mean-field-games-flock-the-reinforcement","title":"Mean Field Games Flock! The Reinforcement Learning Way","date":"2021-05-17","arxiv_id":"2105.07933","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-grit-reinforcement-learning-for-grammar","title":"RL-GRIT: Reinforcement Learning for Grammar Inference","date":"2021-05-17","arxiv_id":"2105.13114","repositories_listed":0,"syntology":null},{"url":null,"slug":"dras-cqsim-a-reinforcement-learning-based","title":"DRAS-CQSim: A Reinforcement Learning based Framework for HPC Cluster Scheduling","date":"2021-05-16","arxiv_id":"2105.07526","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-pac-reinforcement-learning-in","title":"Efficient PAC Reinforcement Learning in Regular Decision Processes","date":"2021-05-14","arxiv_id":"2105.06784","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-interpretable-reinforcement","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","date":"2021-05-14","arxiv_id":"2105.07099","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-warm-start-mcts-in-alphazero-like","title":"Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning","date":"2021-05-13","arxiv_id":"2105.06136","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-safe-decision","title":"Reinforcement Learning Based Safe Decision Making for Highway Autonomous Driving","date":"2021-05-13","arxiv_id":"2105.06517","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-reinforcement-learning-aided","title":"A Survey on Reinforcement Learning-Aided Caching in Mobile Edge Networks","date":"2021-05-12","arxiv_id":"2105.05564","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-reinforcement-learning-in-dynamic","title":"Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control","date":"2021-05-12","arxiv_id":"2105.05817","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-performance-analysis-towards","title":"Interpretable performance analysis towards offline reinforcement learning: A dataset perspective","date":"2021-05-12","arxiv_id":"2105.05473","repositories_listed":0,"syntology":null},{"url":null,"slug":"composable-energy-policies-for-reactive","title":"Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning","date":"2021-05-11","arxiv_id":"2105.04962","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-policy-transfer-in-reinforcement","title":"Adaptive Policy Transfer in Reinforcement Learning","date":"2021-05-10","arxiv_id":"2105.04699","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-self-supervised-data-collection-for","title":"Efficient Self-Supervised Data Collection for Offline Robot Learning","date":"2021-05-10","arxiv_id":"2105.04607","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-free-gradient-temporal-difference","title":"Parameter-free Gradient Temporal Difference Learning","date":"2021-05-10","arxiv_id":"2105.04129","repositories_listed":0,"syntology":null},{"url":null,"slug":"pearl-parallelized-expert-assisted","title":"PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning","date":"2021-05-10","arxiv_id":"2105.04088","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-rare-diffusive","title":"Reinforcement learning of rare diffusive dynamics","date":"2021-05-10","arxiv_id":"2105.04321","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-expert-trajectory","title":"Reinforcement Learning with Expert Trajectory For Quantitative Trading","date":"2021-05-09","arxiv_id":"2105.03844","repositories_listed":0,"syntology":null},{"url":null,"slug":"mctg-multi-frequency-continuous-share-trading","title":"A parallel-network continuous quantitative trading model with GARCH and PPO","date":"2021-05-08","arxiv_id":"2105.03625","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-reinforcement-learning-to-design-an-ai","title":"Using reinforcement learning to design an AI assistantfor a satisfying co-op experience","date":"2021-05-07","arxiv_id":"2105.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-skipped-frames-in-action-repeats","title":"Utilizing Skipped Frames in Action Repeats via Pseudo-Actions","date":"2021-05-07","arxiv_id":"2105.03041","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-graph-convolutional-reinforcement","title":"Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket","date":"2021-05-06","arxiv_id":"2105.08664","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-enhancement-for-deep-reinforcement","title":"Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance","date":"2021-05-05","arxiv_id":"2105.02331","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-sokoban-with-backward-reinforcement","title":"Solving Sokoban with forward-backward reinforcement learning","date":"2021-05-05","arxiv_id":"2105.01904","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-reinforcement-learning-for-1","title":"Data-Efficient Reinforcement Learning for Malaria Control","date":"2021-05-04","arxiv_id":"2105.01620","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-lottery-tickets-and-minimal-task","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","date":"2021-05-04","arxiv_id":"2105.01648","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-linear-convergence-of-natural-policy","title":"On the Linear convergence of Natural Policy Gradient Algorithm","date":"2021-05-04","arxiv_id":"2105.01424","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-scalable-logic","title":"Reinforcement Learning for Scalable Logic Optimization with Graph Neural Networks","date":"2021-05-04","arxiv_id":"2105.01755","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-reward-learning-for","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","date":"2021-05-03","arxiv_id":"2105.00822","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-air","title":"Hierarchical Reinforcement Learning for Air-to-Air Combat","date":"2021-05-03","arxiv_id":"2105.00990","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-swimming-escape-patterns-under","title":"Learning swimming escape patterns for larval fish under energy constraints","date":"2021-05-03","arxiv_id":"2105.00771","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-ridesharing-a","title":"Reinforcement Learning for Ridesharing: An Extended Survey","date":"2021-05-03","arxiv_id":"2105.01099","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoorl-backdoor-attack-against-competitive","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","date":"2021-05-02","arxiv_id":"2105.00579","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-bus-bunching-with-asynchronous-multi","title":"Reducing Bus Bunching with Asynchronous Multi-Agent Reinforcement Learning","date":"2021-05-02","arxiv_id":"2105.00376","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-swarm-collision-avoidance-for","title":"Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning","date":"2021-04-30","arxiv_id":"2104.14912","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-time-mean-field-control-with","title":"Discrete-Time Mean Field Control with Environment States","date":"2021-04-30","arxiv_id":"2104.14900","repositories_listed":0,"syntology":null},{"url":null,"slug":"antagonistic-crowd-simulation-model","title":"Emotional Contagion-Aware Deep Reinforcement Learning for Antagonistic Crowd Simulation","date":"2021-04-29","arxiv_id":"2105.00854","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypernetwork-dismantling-via-deep","title":"Hypernetwork Dismantling via Deep Reinforcement Learning","date":"2021-04-29","arxiv_id":"2104.14332","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-inverse-reinforcement","title":"Adversarial Inverse Reinforcement Learning for Mean Field Games","date":"2021-04-29","arxiv_id":"2104.14654","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-going-on-inside-recurrent-meta","title":"What is Going on Inside Recurrent Meta Reinforcement Learning Agents?","date":"2021-04-29","arxiv_id":"2104.14644","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-environment-for","title":"A Reinforcement Learning Environment for Polyhedral Optimizations","date":"2021-04-28","arxiv_id":"2104.13732","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-adversarial-training-for-meta","title":"Adaptive Adversarial Training for Meta Reinforcement Learning","date":"2021-04-27","arxiv_id":"2104.13302","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-earthquake-like-instabilities","title":"Controlling earthquake-like instabilities using artificial intelligence","date":"2021-04-27","arxiv_id":"2104.13180","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-for-5","title":"A Deep Reinforcement Learning Approach for the Meal Delivery Problem","date":"2021-04-24","arxiv_id":"2104.12000","repositories_listed":0,"syntology":null},{"url":null,"slug":"disco-rl-distribution-conditioned","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","date":"2021-04-23","arxiv_id":"2104.11707","repositories_listed":0,"syntology":null},{"url":null,"slug":"formula-rl-deep-reinforcement-learning-for","title":"Formula RL: Deep Reinforcement Learning for Autonomous Racing using Telemetry Data","date":"2021-04-22","arxiv_id":"2104.11106","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-using-guided","title":"Reinforcement Learning using Guided Observability","date":"2021-04-22","arxiv_id":"2104.10986","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-fusion-for-adaptive-and-customizable","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","date":"2021-04-21","arxiv_id":"2104.10610","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-traffic-signal","title":"Reinforcement Learning for Traffic Signal Control: Comparison with Commercial Systems","date":"2021-04-21","arxiv_id":"2104.10455","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-wide-traffic-signal-control","title":"Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning","date":"2021-04-20","arxiv_id":"2104.09936","repositories_listed":0,"syntology":null},{"url":null,"slug":"outcome-driven-reinforcement-learning-via","title":"Outcome-Driven Reinforcement Learning via Variational Inference","date":"2021-04-20","arxiv_id":"2104.10190","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-synthesis-of-verified-controllers-in","title":"Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning","date":"2021-04-20","arxiv_id":"2104.10219","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-centric-representations-for-multi-agent","title":"Agent-Centric Representations for Multi-Agent Reinforcement Learning","date":"2021-04-19","arxiv_id":"2104.09402","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-multi-agent-fitted-q-iteration","title":"Approximated Multi-Agent Fitted Q Iteration","date":"2021-04-19","arxiv_id":"2104.09343","repositories_listed":0,"syntology":null},{"url":null,"slug":"constraints-satisfiability-driven","title":"Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense","date":"2021-04-19","arxiv_id":"2104.08994","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-in-a-monetary","title":"Deep Reinforcement Learning in a Monetary Model","date":"2021-04-19","arxiv_id":"2104.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-value-aligned-reinforcement-learning","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","date":"2021-04-19","arxiv_id":"2104.09469","repositories_listed":0,"syntology":null},{"url":null,"slug":"mt-opt-continuous-multi-task-robotic","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","date":"2021-04-16","arxiv_id":"2104.08212","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionable-models-unsupervised-offline","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","date":"2021-04-15","arxiv_id":"2104.07749","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-based-interactive-reinforcement-learning","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","date":"2021-04-14","arxiv_id":"2104.06600","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-comfort-aware-reinforcement-learning","title":"Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images","date":"2021-04-14","arxiv_id":"2104.06782","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-reinforcement-learning-for","title":"Data-Driven Reinforcement Learning for Virtual Character Animation Control","date":"2021-04-13","arxiv_id":"2104.06358","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-the-long-term-average-reward-for","title":"Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report","date":"2021-04-13","arxiv_id":"2104.06139","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-admission-control","title":"Reinforcement learning for Admission Control in 5G Wireless Networks","date":"2021-04-13","arxiv_id":"2104.10761","repositories_listed":0,"syntology":null}],"record_sha256":"245cc4fd0c02cee4fafddf236f7f75eeccdb476337fb5af6e1edb06fd4e1b737","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}