{"total":9,"rows":[{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2410.11502","title":"Offline Model-Based Optimization by Learning to Rank","created":"2024-10-15","cited_by_count":13,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2307.04962","title":"Intrinsically motivated graph exploration using network theories of human curiosity","created":"2023-07-11","cited_by_count":3,"area":null},{"id":"2301.06863","title":"A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2307.09109","title":"Mining of Single-Class by Active Learning for Semantic Segmentation","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2511.18958","title":"Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2605.23562","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":null}