{"total":59,"rows":[{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97,"area":null},{"id":"2202.10166","title":"Diffusion Causal Models for Counterfactual Estimation","created":"2022-02-21","cited_by_count":87,"area":null},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2302.02228","title":"Counterfactual Identifiability of Bijective Causal Models","created":"2023-02-04","cited_by_count":43,"area":null},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37,"area":"offlinerl"},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25,"area":null},{"id":"2302.00860","title":"Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries","created":"2023-02-02","cited_by_count":24,"area":"diffusion"},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2603.09030","title":"PlayWorld: Learning Robot World Models from Autonomous Play","created":"2026-03-09","cited_by_count":18,"area":"wm"},{"id":"2301.09031","title":"Counterfactual (Non-)identifiability of Learned Structural Causal Models","created":"2023-01-22","cited_by_count":17,"area":null},{"id":"2111.06888","title":"Learning Generalized Gumbel-max Causal Mechanisms","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2306.01424","title":"Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2306.03929","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2411.16959","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","created":"2024-11-25","cited_by_count":13,"area":"offlinerl"},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2406.03234","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","created":"2024-06-05","cited_by_count":11,"area":"deeprl"},{"id":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2104.12278","title":"Causal Learning for Socially Responsible AI","created":"2021-04-25","cited_by_count":7,"area":null},{"id":"2310.04706","title":"Offline Imitation Learning with Variational Counterfactual Reasoning","created":"2023-10-07","cited_by_count":7,"area":"offlinerl"},{"id":"2510.08294","title":"Counterfactual Identifiability via Dynamic Optimal Transport","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2506.05188","title":"Counterfactual reasoning: an analysis of in-context emergence","created":"2025-06-05","cited_by_count":4,"area":"lr"},{"id":"2108.01358","title":"Accelerating the Learning of TAMER with Counterfactual Explanations","created":"2021-08-03","cited_by_count":3,"area":null},{"id":"2402.02277","title":"Causal Bayesian Optimization via Exogenous Distribution Learning","created":"2024-02-03","cited_by_count":3,"area":null},{"id":"2404.13792","title":"Counterfactual Reasoning Using Predicted Latent Personality Dimensions for Optimizing Persuasion Outcome","created":"2024-04-21","cited_by_count":3,"area":null},{"id":"2406.07685","title":"Test-Time Fairness and Robustness in Large Language Models","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2408.15593","title":"Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning","created":"2024-08-28","cited_by_count":3,"area":"offlinerl"},{"id":"2502.13731","title":"Robust Counterfactual Inference in Markov Decision Processes","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2503.16544","title":"Causal Discovery and Counterfactual Reasoning to Optimize Persuasive Dialogue Policies","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2302.13240","title":"Q-Cogni: An Integrated Causal Reinforcement Learning Framework","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2306.13732","title":"Reinforcement Learning with Temporal-Logic-Based Causal Diagrams","created":"2023-06-23","cited_by_count":2,"area":null},{"id":"2504.13904","title":"Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2507.19882","title":"Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation","created":"2025-07-26","cited_by_count":2,"area":null},{"id":"2306.08537","title":"VIBR: Learning View-Invariant Value Functions for Robust Visual Control","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2310.11334","title":"Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2403.04221","title":"Why Online Reinforcement Learning is Causal","created":"2024-03-07","cited_by_count":1,"area":"offlinerl"},{"id":"2412.11410","title":"MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning","created":"2024-12-16","cited_by_count":1,"area":"offlinerl"},{"id":"2506.23703","title":"A New Perspective On AI Safety Through Control Theory Methodologies","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2603.06946","title":"Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments","created":"2026-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2606.28460","title":"Counterfactual Residual Data Augmentation for Regression","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2402.01607","title":"Natural Counterfactuals With Necessary Backtracking","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2502.06398","title":"Learning Counterfactual Outcomes Under Rank Preservation","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2503.13842","title":"Counterfactual experience augmented off-policy reinforcement learning","created":"2025-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2506.05445","title":"Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic","created":"2025-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2509.00472","title":"Partially Functional Dynamic Backdoor Diffusion-based Causal Model","created":"2025-08-30","cited_by_count":0,"area":"diffusion"},{"id":"2512.09368","title":"CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.09115","title":"Counterfactual Transport Flows for Offline Conservative Trajectory Refinement","created":"2026-06-08","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32247","title":"Certifying Interventional Agreement Among Observationally Equivalent Causal Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33875","title":"Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.08689","title":"Probabilistic Counterfactual Inference for Discrete Outcomes in Gaussian-Process Causal Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.20210","title":"Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}