{"total":70,"rows":[{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100,"area":null},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35,"area":null},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25,"area":null},{"id":"2209.14990","title":"Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms","created":"2022-09-29","cited_by_count":24,"area":null},{"id":"2411.13934","title":"Learning to Cooperate with Humans using Generative Agents","created":"2024-11-21","cited_by_count":24,"area":"agents"},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19,"area":null},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2112.08746","title":"Unsupervised Reinforcement Learning in Multiple Environments","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17,"area":null},{"id":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2110.03743","title":"Reinforcement Learning in Reward-Mixing MDPs","created":"2021-10-07","cited_by_count":15,"area":"alignment"},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2211.09403","title":"Learning Mixtures of Markov Chains and MDPs","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2211.16583","title":"Offline Policy Evaluation and Optimization under Confounding","created":"2022-11-29","cited_by_count":12,"area":"offlinerl"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2303.12287","title":"Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games","created":"2023-03-22","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2412.10419","title":"Preference Adaptive and Sequential Text-to-Image Generation","created":"2024-12-10","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2310.18803","title":"Weakly Coupled Deep Q-Networks","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5,"area":"deeprl"},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2307.02884","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2310.07596","title":"Prospective Side Information for Latent MDPs","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2402.07102","title":"An Empirical Study on the Power of Future Prediction in Partially Observable Environments","created":"2024-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2502.01800","title":"Flow-based Domain Randomization for Learning and Sequencing Robotic Skills","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"id":"2309.14989","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2406.07920","title":"Near-Optimal Learning and Planning in Separated Latent MDPs","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2410.18964","title":"Learning to Look: Seeking Information for Decision Making via Policy Factorization","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2411.00707","title":"Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2510.03207","title":"To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning","created":"2025-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2510.23744","title":"Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2202.05423","title":"Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization","created":"2022-02-11","cited_by_count":2,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2405.16053","title":"Pausing Policy Learning in Non-stationary Reinforcement Learning","created":"2024-05-25","cited_by_count":2,"area":"deeprl"},{"id":"2504.10006","title":"Improving Controller Generalization with Dimensionless Markov Decision Processes","created":"2025-04-14","cited_by_count":2,"area":"deeprl"},{"id":"2307.11704","title":"JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2405.11397","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2504.19715","title":"Model-based controller assisted domain randomization for transient vibration suppression of nonlinear powertrain system with parametric uncertainty","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2505.19574","title":"Situationally-Aware Dynamics Learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.01324","title":"Near-Optimal Clustering in Mixture of Markov Chains","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2301.04268","title":"Adversarial Online Multi-Task Reinforcement Learning","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2306.08762","title":"Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2511.12361","title":"SAC-MoE: Reinforcement Learning with Mixture-of-Experts for Control of Hybrid Dynamical Systems with Uncertainty","created":"2025-11-15","cited_by_count":0,"area":"deeprl"},{"id":"2511.22104","title":"Representative Action Selection for Large Action Space: From Bandits to MDPs","created":"2025-11-27","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}