{"total":61,"rows":[{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2204.11371","title":"Learning Symmetric Embeddings for Equivariant World Models","created":"2022-04-24","cited_by_count":54,"area":"wm"},{"id":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","cited_by_count":49,"area":null},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2303.12410","title":"EDGI: Equivariant Diffusion for Planning with Embodied Agents","created":"2023-03-22","cited_by_count":36,"area":"diffusion"},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","created":"2021-03-29","cited_by_count":32,"area":null},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2404.13478","title":"Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks","created":"2024-04-20","cited_by_count":19,"area":"lr"},{"id":"2201.00248","title":"Transfer RL across Observation Feature Spaces via Model-Based Regularization","created":"2022-01-01","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2102.08291","title":"Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models","created":"2021-02-16","cited_by_count":17,"area":null},{"id":"2207.03116","title":"Equivariant Representation Learning via Class-Pose Decomposition","created":"2022-07-07","cited_by_count":17,"area":null},{"id":"2010.08891","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","created":"2020-10-18","cited_by_count":16,"area":"offlinerl"},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14,"area":"wm"},{"id":"2109.11178","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2503.02143","title":"Four Principles for Physically Interpretable World Models","created":"2025-03-04","cited_by_count":10,"area":"wm"},{"id":"2107.01667","title":"Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces","created":"2021-07-04","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2204.12458","title":"Learning Value Functions from Undirected State-only Experience","created":"2022-04-26","cited_by_count":8,"area":"offlinerl"},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2210.08153","title":"CUP: Critic-Guided Policy Reuse","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2407.13364","title":"Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2405.14114","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","created":"2024-05-23","cited_by_count":5,"area":"offlinerl"},{"id":"2509.23846","title":"Adversarial Diffusion for Robust Reinforcement Learning","created":"2025-09-28","cited_by_count":4,"area":"diffusion"},{"id":"2110.14615","title":"Play to Grade: Testing Coding Games as Classifying Markov Decision Process","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2206.11299","title":"Latent Policies for Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":3,"area":"offlinerl"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2107.01677","title":"Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics","created":"2021-07-04","cited_by_count":2,"area":null},{"id":"2107.11676","title":"The Impact of Negative Sampling on Contrastive Structured World Models","created":"2021-07-24","cited_by_count":2,"area":"wm"},{"id":"2111.10297","title":"Expert-Guided Symmetry Detection in Markov Decision Processes","created":"2021-11-19","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":"2307.08169","title":"Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning","created":"2023-07-16","cited_by_count":2,"area":null},{"id":"2401.14923","title":"Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks","created":"2024-01-26","cited_by_count":2,"area":"alignment"},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2110.07668","title":"Augmenting Imitation Experience via Equivariant Representations","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2112.09943","title":"Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning","created":"2021-12-18","cited_by_count":1,"area":"offlinerl"},{"id":"2308.07351","title":"IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2402.08813","title":"Model approximation in MDPs with unbounded per-step cost","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2410.09686","title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning","created":"2024-10-13","cited_by_count":1,"area":"deeprl"},{"id":"2501.01136","title":"Symmetries-enhanced Multi-Agent Reinforcement Learning","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2506.01529","title":"Learning Abstract World Models with a Group-Structured Latent Space","created":"2025-06-02","cited_by_count":1,"area":"wm"},{"id":"2604.09035","title":"Advantage-Guided Diffusion for Model-Based Reinforcement Learning","created":"2026-04-10","cited_by_count":1,"area":"wm"},{"id":"2106.13237","title":"Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2209.06356","title":"Using Forwards-Backwards Models to Approximate MDP Homomorphisms","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2209.15320","title":"Bounded Robustness in Reinforcement Learning via Lexicographic Objectives","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2301.05231","title":"Equivariant Representation Learning in the Presence of Stabilizers","created":"2023-01-12","cited_by_count":0,"area":null},{"id":"2309.05346","title":"Learning Geometric Representations of Objects via Interaction","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2412.15877","title":"Approximate State Abstraction for Markov Games","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2505.14209","title":"Embedded Mean Field Reinforcement Learning for Perimeter-defense Game","created":"2025-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.12643","title":"Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics","created":"2026-02-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.25357","title":"Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.30743","title":"From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}