{"total":11,"rows":[{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","created":"2021-05-31","cited_by_count":25,"area":null},{"id":"2205.01053","title":"Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes","created":"2022-04-29","cited_by_count":10,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2110.14538","title":"Reinforcement Learning in Factored Action Spaces using Tensor Decompositions","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2304.13571","title":"Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning","created":"2023-04-26","cited_by_count":6,"area":null},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2208.14407","title":"An Analysis of Model-Based Reinforcement Learning From Abstracted Observations","created":"2022-08-30","cited_by_count":2,"area":null},{"id":"2602.17605","title":"Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery","created":"2026-02-19","cited_by_count":0,"area":null}],"next_cursor":null}