{"total":21,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","created":"2022-11-20","cited_by_count":24,"area":null},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2204.13326","title":"Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers","created":"2022-04-28","cited_by_count":6,"area":null},{"id":"2104.03946","title":"Learning What To Do by Simulating the Past","created":"2021-04-08","cited_by_count":4,"area":null},{"id":"2305.17195","title":"Inferring the Future by Imagining the Past","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2102.07017","title":"Mitigating Negative Side Effects via Environment Shaping","created":"2021-02-13","cited_by_count":2,"area":null},{"id":"2305.04692","title":"Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks","created":"2023-05-08","cited_by_count":2,"area":null},{"id":"2307.09692","title":"STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2101.12509","title":"Challenges for Using Impact Regularizers to Avoid Negative Side Effects","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2403.05540","title":"Extinction Risks from AI: Invisible to Science?","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2610.08740","title":"On the Computational Tractability of Robust Bandits","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}