{"total":82,"rows":[{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2203.05194","title":"Learning Torque Control for Quadrupedal Locomotion","created":"2022-03-10","cited_by_count":29,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2307.10142","title":"Benchmarking Potential Based Rewards for Learning Humanoid Locomotion","created":"2023-07-19","cited_by_count":15,"area":null},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2206.00702","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","created":"2022-06-01","cited_by_count":12,"area":null},{"id":"2210.08607","title":"The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2410.01220","title":"Effective Tuning Strategies for Generalist Robot Manipulation Policies","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2205.11184","title":"An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2205.14557","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2210.13611","title":"Understanding the Evolution of Linear Regions in Deep Reinforcement Learning","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2304.10770","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2410.22568","title":"Fast Deep Hedging with Second-Order Optimization","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2301.12802","title":"Planning Multiple Epidemic Interventions with Reinforcement Learning","created":"2023-01-30","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2309.02711","title":"Addressing imperfect symmetry: A novel symmetry-learning actor-critic extension","created":"2023-09-06","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":"2402.04536","title":"Tactile-based Object Retrieval From Granular Media","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2203.06250","title":"Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2310.00112","title":"Reinforcement Learning for Node Selection in Branch-and-Bound","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2104.02372","title":"The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2112.03149","title":"Distilled Domain Randomization","created":"2021-12-06","cited_by_count":3,"area":null},{"id":"2305.13164","title":"INVICTUS: Optimizing Boolean Logic Circuit Synthesis via Synergistic Learning and Search","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2506.13755","title":"MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2101.04167","title":"First-Order Problem Solving through Neural MCTS based Reinforcement Learning","created":"2021-01-11","cited_by_count":2,"area":null},{"id":"2209.09344","title":"Understanding reinforcement learned crowds","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2201.12819","title":"A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms","created":"2022-01-30","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2210.13011","title":"On Many-Actions Policy Gradient","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2301.03679","title":"Transformers as Policies for Variable Action Environments","created":"2023-01-09","cited_by_count":1,"area":null},{"id":"2304.10277","title":"Robust nonlinear set-point control with reinforcement learning","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2304.10289","title":"Aiding reinforcement learning for set point control","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2308.01910","title":"Deep Policy Gradient Methods in Commodity Markets","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2507.08726","title":"Learning human-to-robot handovers through 3D scene reconstruction","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2510.11824","title":"Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2512.01467","title":"Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2108.09478","title":"MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl","created":"2021-08-21","cited_by_count":0,"area":null},{"id":"2204.07134","title":"Reinforcement Learning Policy Recommendation for Interbank Network Stability","created":"2022-04-14","cited_by_count":0,"area":null},{"id":"2206.02855","title":"Efficient entity-based reinforcement learning","created":"2022-06-06","cited_by_count":0,"area":null},{"id":"2211.06236","title":"Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2211.13474","title":"Explainable and Safe Reinforcement Learning for Autonomous Air Mobility","created":"2022-11-24","cited_by_count":0,"area":null},{"id":"2211.17013","title":"Climate Change Policy Exploration using Reinforcement Learning","created":"2022-10-23","cited_by_count":0,"area":null},{"id":"2212.14214","title":"Backward Curriculum Reinforcement Learning","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2309.00630","title":"Commodities Trading through Deep Policy Gradient Methods","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2309.12841","title":"Reward Function Design for Crowd Simulation via Reinforcement Learning","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2403.06750","title":"Generalising Multi-Agent Cooperation through Task-Agnostic Communication","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2404.13142","title":"Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning","created":"2024-04-19","cited_by_count":0,"area":null},{"id":"2602.08403","title":"Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.30719","title":"When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.11349","title":"Dynamics Models for Offline Hyperparameter Selection in Real-World RL","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.00189","title":"Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.02828","title":"FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08541","title":"Micro Neural Policies for Safe Real-Time Robotic Control","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}