{"total":69,"rows":[{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40,"area":null},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"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":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"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":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"area":"deeprl"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2510.09976","title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models","created":"2025-10-11","cited_by_count":9,"area":"vla"},{"id":"2407.19943","title":"Practical and Robust Safety Guarantees for Advanced Counterfactual Learning to Rank","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2505.09371","title":"TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search","created":"2025-05-14","cited_by_count":7,"area":"deeprl"},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2602.12691","title":"ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training","created":"2026-02-13","cited_by_count":7,"area":"vla"},{"id":"2203.09809","title":"Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio","created":"2022-03-18","cited_by_count":5,"area":null},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2202.06253","title":"Autonomous Drone Swarm Navigation and Multi-target Tracking in 3D Environments with Dynamic Obstacles","created":"2022-02-13","cited_by_count":4,"area":null},{"id":"2506.03757","title":"PPO in the Fisher-Rao geometry","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2602.02150","title":"ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2206.10606","title":"Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3,"area":null},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2511.19528","title":"Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories","created":"2025-11-24","cited_by_count":3,"area":"vla"},{"id":"2601.22801","title":"Clipping-Free Policy Optimization for Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"alignment"},{"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":"2606.10968","title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2306.01451","title":"Deep Q-Learning versus Proximal Policy Optimization: Performance Comparison in a Material Sorting Task","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2310.13230","title":"Absolute Policy Optimization","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2507.12189","title":"BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture search","created":"2025-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2603.19741","title":"FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment","created":"2026-03-20","cited_by_count":2,"area":"alignment"},{"id":"2110.10522","title":"CIM-PPO:Proximal Policy Optimization with Liu-Correntropy Induced Metric","created":"2021-10-20","cited_by_count":1,"area":null},{"id":"2204.05627","title":"Proximal Policy Optimization Learning based Control of Congested Freeway Traffic","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2206.13714","title":"Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse","created":"2022-06-28","cited_by_count":1,"area":null},{"id":"2303.15453","title":"Robustness of Utilizing Feedback in Embodied Visual Navigation","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2310.18354","title":"A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare","created":"2023-10-23","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":"2409.01427","title":"Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization","created":"2024-09-02","cited_by_count":1,"area":"diffusion"},{"id":"2603.01365","title":"Align and Filter: Improving Performance in Asynchronous On-Policy RL","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.03955","title":"GIPO: Gaussian Importance Sampling Policy Optimization","created":"2026-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2606.13682","title":"A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem","created":"2026-03-25","cited_by_count":1,"area":"deeprl"},{"id":"2208.09322","title":"Entropy Augmented Reinforcement Learning","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2301.10919","title":"Joint action loss for proximal policy optimization","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2301.10920","title":"Partial advantage estimator for proximal policy optimization","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2304.12431","title":"Neuroevolution of Recurrent Architectures on Control Tasks","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2308.06741","title":"Heterogeneous Multi-Agent Reinforcement Learning via Mirror Descent Policy Optimization","created":"2023-08-13","cited_by_count":0,"area":null},{"id":"2405.03711","title":"Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2407.09551","title":"Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback","created":"2024-06-27","cited_by_count":0,"area":"diffusion"},{"id":"2408.16069","title":"Hitting the Gym: Reinforcement Learning Control of Exercise-Strengthened Biohybrid Robots in Simulation","created":"2024-08-28","cited_by_count":0,"area":"deeprl"},{"id":"2412.19578","title":"Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization","created":"2024-12-27","cited_by_count":0,"area":"deeprl"},{"id":"2509.20265","title":"Failure Modes of Maximum Entropy RLHF","created":"2025-09-24","cited_by_count":0,"area":"alignment"},{"id":"2511.02577","title":"Directional-Clamp PPO","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2511.23148","title":"Peer-to-Peer Energy Trading in Dairy Farms using Multi-Agent Reinforcement Learning","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2603.28421","title":"Learning Unified Control of Intrinsic Nonlinear Spin Dynamics in Atomic Qudits for Magnetometry","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.18578","title":"Bounded Ratio Reinforcement Learning","created":"2026-04-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.02320","title":"ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields","created":"2026-05-04","cited_by_count":0,"area":"alignment"},{"id":"2605.09212","title":"Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.23932","title":"KLip-PPO: A per-sample KL perspective on PPO-Clip","created":"2026-06-22","cited_by_count":0,"area":"deeprl"},{"id":"2607.10848","title":"Predictive Divergence Masks for LLM RL","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.18163","title":"OR Else: A Differentiable Trust Region for Policy Optimization","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2610.01399","title":"Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}