{"total":133,"rows":[{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41,"area":null},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36,"area":null},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"id":"2101.03864","title":"Deep Interactive Bayesian Reinforcement Learning via Meta-Learning","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2305.09648","title":"Prompt-Tuning Decision Transformer with Preference Ranking","created":"2023-05-16","cited_by_count":19,"area":null},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18,"area":null},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18,"area":null},{"id":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","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":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2309.14970","title":"Recurrent Hypernetworks are Surprisingly Strong in Meta-RL","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2212.12735","title":"An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context","created":"2022-12-24","cited_by_count":15,"area":null},{"id":"2302.03067","title":"Memory-Based Meta-Learning on Non-Stationary Distributions","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2206.05240","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2210.11579","title":"Model-based Lifelong Reinforcement Learning with Bayesian Exploration","created":"2022-10-20","cited_by_count":12,"area":null},{"id":"2301.11147","title":"Train Hard, Fight Easy: Robust Meta Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2504.19139","title":"Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments","created":"2025-04-27","cited_by_count":12,"area":null},{"id":"2111.00134","title":"Context Meta-Reinforcement Learning via Neuromodulation","created":"2021-10-30","cited_by_count":11,"area":null},{"id":"2210.03104","title":"Distributionally Adaptive Meta Reinforcement Learning","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2108.03718","title":"Meta-Reinforcement Learning in Broad and Non-Parametric Environments","created":"2021-08-08","cited_by_count":10,"area":null},{"id":"2305.00286","title":"Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning","created":"2023-04-29","cited_by_count":10,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2202.06557","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution","created":"2022-02-14","cited_by_count":9,"area":null},{"id":"2306.02418","title":"ContraBAR: Contrastive Bayes-Adaptive Deep RL","created":"2023-06-04","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2101.00746","title":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","created":"2021-01-04","cited_by_count":8,"area":null},{"id":"2105.08834","title":"Meta-Reinforcement Learning by Tracking Task Non-stationarity","created":"2021-05-18","cited_by_count":8,"area":null},{"id":"2205.15879","title":"Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2109.11792","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2309.14078","title":"ODE-based Recurrent Model-free Reinforcement Learning for POMDPs","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2402.08369","title":"One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2110.04074","title":"Active inference, Bayesian optimal design, and expected utility","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2111.12146","title":"Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review","created":"2021-11-23","cited_by_count":6,"area":null},{"id":"2112.00478","title":"On the Practical Consistency of Meta-Reinforcement Learning Algorithms","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2206.10716","title":"Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2211.08802","title":"Giving Feedback on Interactive Student Programs with Meta-Exploration","created":"2022-11-16","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":"2106.13125","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2111.00206","title":"One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2112.07328","title":"Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning","created":"2021-12-14","cited_by_count":5,"area":null},{"id":"2206.12765","title":"Generalized Beliefs for Cooperative AI","created":"2022-06-26","cited_by_count":5,"area":null},{"id":"2207.02249","title":"Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2210.00350","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2310.03984","title":"AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2109.09031","title":"Hindsight Foresight Relabeling for Meta-Reinforcement Learning","created":"2021-09-18","cited_by_count":4,"area":null},{"id":"2201.08732","title":"Meta Learning MDPs with Linear Transition Models","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2202.02363","title":"Meta-Reinforcement Learning with Self-Modifying Networks","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2205.09546","title":"Deterministic training of generative autoencoders using invertible layers","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2211.10861","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","created":"2022-11-20","cited_by_count":4,"area":null},{"id":"2302.07958","title":"Meta-Reinforcement Learning via Exploratory Task Clustering","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2304.00354","title":"On Context Distribution Shift in Task Representation Learning for Offline Meta RL","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2306.02747","title":"Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2307.02276","title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2307.05891","title":"PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks","created":"2023-07-12","cited_by_count":4,"area":null},{"id":"2310.12862","title":"Fine-Tuning Generative Models as an Inference Method for Robotic Tasks","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2408.06542","title":"Value of Information and Reward Specification in Active Inference and POMDPs","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2106.03279","title":"Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2208.11535","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2211.07614","title":"Towards Data-Driven Offline Simulations for Online Reinforcement Learning","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2105.06660","title":"Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2110.15489","title":"GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL","created":"2021-10-29","cited_by_count":2,"area":null},{"id":"2210.16530","title":"BIMRL: Brain Inspired Meta Reinforcement Learning","created":"2022-10-29","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null}],"next_cursor":"100"}