{"total":79,"rows":[{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512,"area":"wm"},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2110.02544","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","created":"2021-10-06","cited_by_count":108,"area":null},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27,"area":"deeprl"},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2111.03941","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","created":"2021-11-06","cited_by_count":23,"area":null},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2103.06484","title":"Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2206.08737","title":"N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments","created":"2022-06-17","cited_by_count":16,"area":null},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"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":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2112.11622","title":"An Alternate Policy Gradient Estimator for Softmax Policies","created":"2021-12-22","cited_by_count":9,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2204.06117","title":"AdaTest:Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2310.17485","title":"Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2406.01853","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2308.12772","title":"Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2401.09286","title":"Deployable Reinforcement Learning with Variable Control Rate","created":"2024-01-17","cited_by_count":5,"area":"deeprl"},{"id":"2403.03552","title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning","created":"2024-03-06","cited_by_count":5,"area":"deeprl"},{"id":"2410.01431","title":"Scalable Reinforcement Learning-based Neural Architecture Search","created":"2024-10-02","cited_by_count":5,"area":"deeprl"},{"id":"2505.23436","title":"Emergent Risk Awareness in Rational Agents under Resource Constraints","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2405.01684","title":"Intelligent Switching for Reset-Free RL","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2402.14961","title":"Reinforcement Learning with Elastic Time Steps","created":"2024-02-22","cited_by_count":3,"area":"deeprl"},{"id":"2406.01641","title":"Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents","created":"2024-06-03","cited_by_count":3,"area":"deeprl"},{"id":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2210.14428","title":"D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning","created":"2022-10-26","cited_by_count":2,"area":"offlinerl"},{"id":"2212.04136","title":"Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2301.02593","title":"Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads","created":"2023-01-06","cited_by_count":2,"area":null},{"id":"2304.12330","title":"Parallel bootstrap-based on-policy deep reinforcement learning for continuous flow control applications","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2305.18701","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2307.08794","title":"Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning","created":"2023-07-17","cited_by_count":2,"area":null},{"id":"2111.06780","title":"AWD3: Dynamic Reduction of the Estimation Bias","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2302.01301","title":"MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2401.09840","title":"FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2407.03311","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2410.22203","title":"Democratizing Reward Design for Personal and Representative Value-Alignment","created":"2024-10-29","cited_by_count":1,"area":"alignment"},{"id":"2512.06252","title":"Learning Without Time-Based Embodiment Resets in Soft-Actor Critic","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2602.04131","title":"Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting","created":"2026-02-04","cited_by_count":1,"area":"deeprl"},{"id":"2604.07672","title":"Reset-Free Reinforcement Learning for Real-World Agile Driving: An Empirical Study","created":"2026-04-09","cited_by_count":1,"area":"driving"},{"id":"2605.29860","title":"ESPO: Early-Stopping Proximal Policy Optimization","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2607.13028","title":"TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale","created":"2026-07-14","cited_by_count":1,"area":"driving"},{"id":"2211.07434","title":"Parallel Automatic History Matching Algorithm Using Reinforcement Learning","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2211.08272","title":"Low-Thrust Orbital Transfer using Dynamics-Agnostic Reinforcement Learning","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2403.00673","title":"Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency","created":"2024-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2410.06317","title":"Learning in complex action spaces without policy gradients","created":"2024-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2412.01420","title":"Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning","created":"2024-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2505.07832","title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2506.19353","title":"Partially Observable Residual Reinforcement Learning for PV-Inverter-Based Voltage Control in Distribution Grids","created":"2025-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2509.23556","title":"Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement Learning","created":"2025-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2603.16842","title":"Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search","created":"2026-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2604.19033","title":"Intentional Updates for Streaming Reinforcement Learning","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.19166","title":"A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.04574","title":"Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.19752","title":"Temporal Self-Imitation Learning","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2606.21587","title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","created":"2026-06-19","cited_by_count":0,"area":"driving"},{"id":"2608.14940","title":"When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.17289","title":"PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2608.27678","title":"SegBench-GC: Testing Segmentation Invariance in Multi-Step Offline Goal-Conditioned Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.05569","title":"Information-Guided Safe Reinforcement Learning for Autonomous Gas Source Localization using sUAS","created":"2026-09-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.05446","title":"Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.07562","title":"Learning a Mixture of GFlowNets","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.19614","title":"Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}