{"total":21,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43,"area":null},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2303.08060","title":"Beyond Games: A Systematic Review of Neural Monte Carlo Tree Search Applications","created":"2023-03-14","cited_by_count":16,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2312.01624","title":"GVFs in the Real World: Making Predictions Online for Water Treatment","created":"2023-12-04","cited_by_count":13,"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":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2310.12819","title":"Hybrid Search for Efficient Planning with Completeness Guarantees","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2306.04403","title":"Policy-Based Self-Competition for Planning Problems","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2303.05205","title":"Real-time scheduling of renewable power systems through planning-based reinforcement learning","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2308.16215","title":"Deep Video Codec Control for Vision Models","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2401.10149","title":"Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2501.12216","title":"RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2404.12330","title":"A Perspective on Deep Vision Performance with Standard Image and Video Codecs","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2411.04580","title":"Demystifying MuZero Planning: Interpreting the Learned Model","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2306.03408","title":"Agents Explore the Environment Beyond Good Actions to Improve Their Model for Better Decisions","created":"2023-06-06","cited_by_count":0,"area":null}],"next_cursor":null}