{"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-2/papers/100","list_of":"/task/reinforcement-learning-2","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":100,"pages_in_order":135,"rows_per_page":100,"rows":[9901,10000],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2","prev":"/task/reinforcement-learning-2/papers/99","next":"/task/reinforcement-learning-2/papers/101","papers":[{"url":null,"slug":"enhanced-pub-sub-communications-for-massive","title":"Enhanced Pub/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning","date":"2021-01-03","arxiv_id":"2101.00687","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-learning-and-communication-framework","title":"Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels","date":"2021-01-02","arxiv_id":"2101.10369","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-safe-reinforcement-learning-for","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","date":"2021-01-02","arxiv_id":"2101.00531","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-flexibility-design-1","title":"Reinforcement Learning for Flexibility Design Problems","date":"2021-01-02","arxiv_id":"2101.00355","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reduction-approach-to-constrained","title":"A Reduction Approach to Constrained Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-fuel-optimization-strategy-for","title":"A Robust Fuel Optimization Strategy For Hybrid Electric Vehicles: A Deep Reinforcement Learning Based Continuous Time Design Approach","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-reinforcement-learning-for","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","date":"2021-01-01","arxiv_id":"2101.00240","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-learning-rates-for-multi-agent","title":"Adaptive Learning Rates for Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-multi-model-fusion-learning-for","title":"Adaptive Multi-model Fusion Learning for Sparse-Reward Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-distribution-shift-in-online","title":"Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-extrapolation-error-in-deep","title":"Addressing Extrapolation Error in Deep Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alpha-dag-a-reinforcement-learning-based","title":"Alpha-DAG: a reinforcement learning based algorithm to learn Directed Acyclic Graphs","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-examination-of-preference-based","title":"An Examination of Preference-based Reinforcement Learning for Treatment Recommendation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-pareto-frontier-through","title":"Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aspect-based-sentiment-classification-via","title":"Aspect-based Sentiment Classification via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-driven-robotic-manipulation","title":"Attention-driven Robotic Manipulation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"average-reward-reinforcement-learning-with-1","title":"Average Reward Reinforcement Learning with Monotonic Policy Improvement","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-reinforcement-learning-through","title":"Batch Reinforcement Learning Through Continuation Method","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-multi-agent-deep-reinforcement","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bounded-myopic-adversaries-for-deep","title":"Bounded Myopic Adversaries for Deep Reinforcement Learning Agents","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"brac-going-deeper-with-behavior-regularized","title":"BRAC+: Going Deeper with Behavior Regularized Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-imitation-and-reinforcement","title":"Combining Imitation and Reinforcement Learning with Free Energy Principle","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-in-multi-agent-reinforcement","title":"Communication in Multi-Agent Reinforcement Learning: Intention Sharing","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compute-and-memory-efficient-reinforcement","title":"Compute- and Memory-Efficient Reinforcement Learning with Latent Experience Replay","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-reinforcement-learning-with","title":"Constrained Reinforcement Learning With Learned Constraints","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinated-multi-agent-exploration-using","title":"Coordinated Multi-Agent Exploration Using Shared Goals","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-state-self-constraint-for-feature","title":"Cross-State Self-Constraint for Feature Generalization in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"daylight-assessing-generalization-skills-of","title":"Daylight: Assessing Generalization Skills of Deep Reinforcement Learning Agents","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adaptive","title":"Deep Reinforcement Learning With Adaptive Combined Critics","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-reinforcement-learning-for-2","title":"Distributional Reinforcement Learning for Risk-Sensitive Policies","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entropic-risk-sensitive-reinforcement","title":"Entropic Risk-Sensitive Reinforcement Learning: A Meta Regret Framework with Function Approximation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"error-controlled-actor-critic-method-to","title":"Error Controlled Actor-Critic Method to Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-reinforcement-learning-through","title":"Explainable Reinforcement Learning Through Goal-Based Explanations","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-pareto-front-optimization-for","title":"Explicit Pareto Front Optimization for Constrained Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-with-dynamic-map-graph-structured","title":"Explore with Dynamic Map: Graph Structured Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-transferability-of-perturbations-in","title":"Exploring Transferability of Perturbations in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"factored-action-spaces-in-deep-reinforcement","title":"Factored Action Spaces in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"factoredrl-leveraging-factored-graphs-for","title":"FactoredRL: Leveraging Factored Graphs for Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-offline-reinforcement-learning","title":"Fine-Tuning Offline Reinforcement Learning with Model-Based Policy Optimization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fsv-learning-to-factorize-soft-value-function","title":"FSV: Learning to Factorize Soft Value Function for Cooperative Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"genetic-soft-updates-for-policy-evolution-in","title":"Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-to-entities-for","title":"Grounding Language to Entities for Generalization in Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-learning-to-branch-via","title":"Improving Learning to Branch via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-policy-gradients-for-online","title":"Incremental Policy Gradients for Online Reinforcement Learning Control","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-meta-reinforcement-learning","title":"Interpretable Meta-Reinforcement Learning with Actor-Critic Method","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-reinforcement-learning-with-1","title":"Interpretable Reinforcement Learning With Neural Symbolic Logic","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsically-guided-exploration-in-meta","title":"Intrinsically Guided Exploration in Meta Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-representations-for-reinforcement","title":"Invariant Representations for Reinforcement Learning without Reconstruction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-reinforcement-learning-for-autonomous","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","date":"2021-01-01","arxiv_id":"2101.00186","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-transferable-scheduling-policy-for","title":"Learning a Transferable Scheduling Policy for Various Vehicle Routing Problems based on Graph-centric Representation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-demonstrations-with-energy","title":"Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-latent-landmarks-for-generalizable","title":"Learning Latent Landmarks for Generalizable Planning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-predictive-communication-by","title":"Learning Predictive Communication by Imagination in Networked System Control","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-communicate-through-imagination","title":"Learning to communicate through imagination with model-based deep multi-agent reinforcement learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-observe-with-reinforcement","title":"Learning to Observe with Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-with-informed","title":"Meta-Reinforcement Learning With Informed Policy Regularization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-planning-and-learning-with","title":"Monte-Carlo Planning and Learning with Language Action Value Estimates","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mqes-max-q-entropy-search-for-efficient","title":"MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-trade-offs-of-image-prediction-in-visual","title":"On Trade-offs of Image Prediction in Visual Model-Based Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-exploration-with-backward","title":"Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-policy-optimization-with-general","title":"Optimistic Policy Optimization with General Function Approximations","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-information-bottleneck-in","title":"Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"peril-probabilistic-embeddings-for-hybrid","title":"PERIL: Probabilistic Embeddings for hybrid Meta-Reinforcement and Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-based-asymptotically-equivalent-reward","title":"Plan-Based Asymptotically Equivalent Reward Shaping","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-atari-with-capsule-networks-a","title":"Playing Atari with Capsule Networks: A systematic comparison of CNN and CapsNets-based agents.","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-marginalized-importance-sampling","title":"Practical Marginalized Importance Sampling with the Successor Representation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-rich-observation-reinforcement","title":"Provable Rich Observation Reinforcement Learning with Combinatorial Latent States","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"r-latte-attention-module-for-visual-control","title":"R-LAtte: Attention Module for Visual Control via Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"re-examining-routing-networks-for-multi-task","title":"Re-examining Routing Networks for Multi-task Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reconnaissance-for-reinforcement-learning","title":"RECONNAISSANCE FOR REINFORCEMENT LEARNING WITH SAFETY CONSTRAINTS","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regioned-episodic-reinforcement-learning","title":"Regioned Episodic Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-asymmetrical-dnn","title":"Reinforcement Learning Based Asymmetrical DNN Modularization for Optimal Loading","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-control-with","title":"Reinforcement Learning for Control with Probabilistic Stability Guarantee","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-bayesian","title":"Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-balancing-offline-model-based","title":"Representation Balancing Offline Model-based Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rmix-risk-sensitive-multi-agent-reinforcement","title":"RMIX: Risk-Sensitive Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-imitation-via-decision-time-planning","title":"Robust Imitation via Decision-Time Planning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-agent-reinforcement-learning","title":"Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-offline-reinforcement-learning-from","title":"Robust Offline Reinforcement Learning from Low-Quality Data","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-bayesian-inverse-reinforcement","title":"Scalable Bayesian Inverse Reinforcement Learning by Auto-Encoding Reward","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"schedulenet-learn-to-solve-minmax-mtsp-using","title":"ScheduleNet: Learn to Solve MinMax mTSP Using Reinforcement Learning with Delayed Reward","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-continuous-control-without","title":"Self-Supervised Continuous Control without Policy Gradient","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"success-rate-targeted-reinforcement-learning","title":"Success-Rate Targeted Reinforcement Learning by Disorientation Penalty","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-skill-action-architecture-learning","title":"The Skill-Action Architecture: Learning Abstract Action Embeddings for Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-learning-with-state-conditioned","title":"Unbiased learning with State-Conditioned Rewards in Adversarial Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-weighted-offline-reinforcement","title":"Uncertainty Weighted Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-leveraging-causal-relations","title":"Understanding and Leveraging Causal Relations in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-active-pre-training-for","title":"Unsupervised Active Pre-Training for Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"updet-universal-multi-agent-rl-via-policy","title":"UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-with-reinforcement-learning","title":"Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-are-the-statistical-limits-of-batch-rl","title":"What are the Statistical Limits of Batch RL with Linear Function Approximation?","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-generalizable-reinforcement-learning","title":"When Is Generalizable Reinforcement Learning Tractable?","date":"2021-01-01","arxiv_id":"2101.00300","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-maintenance-in-iot-networks-via","title":"Autonomous Maintenance in IoT Networks via AoI-driven Deep Reinforcement Learning","date":"2020-12-31","arxiv_id":"2012.15548","repositories_listed":0,"syntology":null},{"url":null,"slug":"curriculum-based-deep-reinforcement-learning","title":"Curriculum-based Deep Reinforcement Learning for Quantum Control","date":"2020-12-31","arxiv_id":"2012.15427","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-deep-reinforcement-learning-for","title":"Relational Deep Reinforcement Learning for Routing in Wireless Networks","date":"2020-12-31","arxiv_id":"2012.15700","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-reliable-designs-of-data-driven","title":"Toward Reliable Designs of Data-Driven Reinforcement Learning Tracking Control for Euler-Lagrange Systems","date":"2020-12-31","arxiv_id":"2101.00068","repositories_listed":0,"syntology":null},{"url":null,"slug":"lispr-an-options-framework-for-policy-reuse","title":"LISPR: An Options Framework for Policy Reuse with Reinforcement Learning","date":"2020-12-29","arxiv_id":"2012.14942","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-multi-agent-actor-critic-learning","title":"Federated Multi-Agent Actor-Critic Learning for Age Sensitive Mobile Edge Computing","date":"2020-12-28","arxiv_id":"2012.14137","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitive-deep-rl-variance-constrained","title":"Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy","date":"2020-12-28","arxiv_id":"2012.14098","repositories_listed":0,"syntology":null},{"url":null,"slug":"portfolio-optimization-with-2d-relative","title":"Portfolio Optimization with 2D Relative-Attentional Gated Transformer","date":"2020-12-27","arxiv_id":"2101.03138","repositories_listed":0,"syntology":null}],"record_sha256":"2c68b1043f3a5d1d88a1e28fc443ae65c79c3d018ddb444e8897f10208aa1c61","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}