{"total":109,"rows":[{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2301.04462","title":"An Analysis of Quantile Temporal-Difference Learning","created":"2023-01-11","cited_by_count":31,"area":null},{"id":"2302.05793","title":"Distributional GFlowNets with Quantile Flows","created":"2023-02-11","cited_by_count":28,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2310.05858","title":"Distributional Soft Actor-Critic with Three Refinements","created":"2023-10-09","cited_by_count":25,"area":null},{"id":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24,"area":null},{"id":"2110.15335","title":"Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning","created":"2021-10-28","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22,"area":null},{"id":"2412.13211","title":"ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks","created":"2024-12-09","cited_by_count":22,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2108.13680","title":"Learning Practically Feasible Policies for Online 3D Bin Packing","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2101.08477","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2105.11366","title":"GMAC: A Distributional Perspective on Actor-Critic Framework","created":"2021-05-24","cited_by_count":16,"area":null},{"id":"2205.11051","title":"Flow-based Recurrent Belief State Learning for POMDPs","created":"2022-05-23","cited_by_count":16,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","cited_by_count":14,"area":null},{"id":"2212.02094","title":"Learning Physically Realizable Skills for Online Packing of General 3D Shapes","created":"2022-12-05","cited_by_count":12,"area":null},{"id":"2310.20266","title":"Beyond Average Return in Markov Decision Processes","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2102.13446","title":"Safe Distributional Reinforcement Learning","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2103.08233","title":"Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning","created":"2021-03-15","cited_by_count":10,"area":null},{"id":"2112.06061","title":"OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion","created":"2021-12-11","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2311.01642","title":"Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula","created":"2023-11-03","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2207.13131","title":"Semi-analytical Industrial Cooling System Model for Reinforcement Learning","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2111.10898","title":"Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning","created":"2021-11-21","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2110.00704","title":"OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation","created":"2021-10-02","cited_by_count":7,"area":null},{"id":"2202.00088","title":"Reinforcement Learning with Heterogeneous Data: Estimation and Inference","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2206.01162","title":"Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2204.10256","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","created":"2022-04-21","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2102.12103","title":"FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism","created":"2021-02-24","cited_by_count":5,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2110.09904","title":"Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space","created":"2021-10-19","cited_by_count":5,"area":null},{"id":"2111.12600","title":"Learning State Representations via Retracing in Reinforcement Learning","created":"2021-11-24","cited_by_count":5,"area":null},{"id":"2112.12740","title":"Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2210.11262","title":"RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2102.12962","title":"Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning","created":"2021-02-25","cited_by_count":4,"area":null},{"id":"2106.02681","title":"SpikePropamine: Differentiable Plasticity in Spiking Neural Networks","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2103.02225","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","created":"2021-03-03","cited_by_count":3,"area":null},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2203.10844","title":"Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3,"area":null},{"id":"2311.10937","title":"Bridging Data-Driven and Knowledge-Driven Approaches for Safety-Critical Scenario Generation in Automated Vehicle Validation","created":"2023-11-18","cited_by_count":3,"area":null},{"id":"2312.15474","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","created":"2023-12-24","cited_by_count":3,"area":null},{"id":"2608.02181","title":"Start Classifying: Categorical Critics for LLM Reinforcement Learning","created":"2026-08-03","cited_by_count":3,"area":null},{"id":"2102.10357","title":"How To Train Your HERON","created":"2021-02-20","cited_by_count":2,"area":null},{"id":"2209.08112","title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2211.11940","title":"Decision-making with Speculative Opponent Models","created":"2022-11-22","cited_by_count":2,"area":null},{"id":"2211.14426","title":"A Critical Review of Traffic Signal Control and A Novel Unified View of Reinforcement Learning and Model Predictive Control Approaches for Adaptive Traffic Signal Control","created":"2022-11-26","cited_by_count":2,"area":null},{"id":"2305.17552","title":"Online Nonstochastic Model-Free Reinforcement Learning","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2306.06637","title":"PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm","created":"2023-06-11","cited_by_count":2,"area":null},{"id":"2312.06126","title":"Spreeze: High-Throughput Parallel Reinforcement Learning Framework","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2410.07174","title":"Neural Circuit Architectural Priors for Quadruped Locomotion","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2106.10533","title":"Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information","created":"2021-06-19","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2109.02791","title":"Safety-Critical Learning of Robot Control with Temporal Logic Specifications","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2203.09565","title":"Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2206.05860","title":"IGN : Implicit Generative Networks","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2208.13125","title":"Normality-Guided Distributional Reinforcement Learning for Continuous Control","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2302.00533","title":"Distillation Policy Optimization","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2303.13657","title":"Policy Evaluation in Distributional LQR","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.03870","title":"Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2308.10203","title":"Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2411.01121","title":"Hedging and Pricing Structured Products Featuring Multiple Underlying Assets","created":"2024-11-02","cited_by_count":1,"area":null},{"id":"2102.11717","title":"Greedy-Step Off-Policy Reinforcement Learning","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2106.02943","title":"Learning Routines for Effective Off-Policy Reinforcement Learning","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2108.12916","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2112.09854","title":"Space Non-cooperative Object Active Tracking with Deep Reinforcement Learning","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2202.00360","title":"Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies","created":"2022-02-01","cited_by_count":0,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2210.04820","title":"Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2212.14262","title":"Invariance to Quantile Selection in Distributional Continuous Control","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2301.03887","title":"Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework","created":"2023-01-10","cited_by_count":0,"area":null},{"id":"2302.05838","title":"Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2305.18501","title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm","created":"2023-05-29","cited_by_count":0,"area":null}],"next_cursor":"100"}