{"total":53,"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":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71,"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":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2107.02776","title":"Counterfactual Explanations in Sequential Decision Making Under Uncertainty","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2111.07603","title":"Counterfactual Temporal Point Processes","created":"2021-11-15","cited_by_count":20,"area":null},{"id":"2110.13891","title":"Dynamic Causal Bayesian Optimization","created":"2021-10-26","cited_by_count":17,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2111.06888","title":"Learning Generalized Gumbel-max Causal Mechanisms","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2102.02671","title":"Directive Explanations for Actionable Explainability in Machine Learning Applications","created":"2021-02-03","cited_by_count":14,"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":"2409.17027","title":"Counterfactual Token Generation in Large Language Models","created":"2024-09-25","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":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2206.04890","title":"Adversarial Counterfactual Environment Model Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2205.13832","title":"Counterfactual Analysis in Dynamic Latent State Models","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2204.00302","title":"Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes","created":"2022-04-01","cited_by_count":8,"area":null},{"id":"2210.16838","title":"Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2212.03974","title":"Counterfactuals for the Future","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2108.01358","title":"Accelerating the Learning of TAMER with Counterfactual Explanations","created":"2021-08-03","cited_by_count":3,"area":null},{"id":"2302.12676","title":"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2312.13628","title":"Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples","created":"2023-12-21","cited_by_count":3,"area":null},{"id":"2502.13731","title":"Robust Counterfactual Inference in Markov Decision Processes","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2106.00266","title":"Did I do that? Blame as a means to identify controlled effects in reinforcement learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2106.05659","title":"Next-Gen Machine Learning Supported Diagnostic Systems for Spacecraft","created":"2021-06-10","cited_by_count":2,"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":"2411.07832","title":"Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2512.01827","title":"CauSight: Learning to Supersense for Visual Causal Discovery","created":"2025-12-01","cited_by_count":2,"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":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","cited_by_count":1,"area":null},{"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":"2507.09961","title":"Text-Driven Causal Representation Learning for Source-Free Domain Generalization","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2602.14791","title":"Extending Multi-Source Bayesian Optimization With Causality Principles","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2112.05519","title":"A Validation Tool for Designing Reinforcement Learning Environments","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2202.01108","title":"Learning to reason about and to act on physical cascading events","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2307.11785","title":"Adversarial Conversational Shaping for Intelligent Agents","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2309.08332","title":"Estimation of Counterfactual Interventions under Uncertainties","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2312.08724","title":"Personalized Path Recourse for Reinforcement Learning Agents","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2404.14418","title":"Mitigating Cascading Effects in Large Adversarial Graph Environments","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2603.18968","title":"Teleological Inference in Structural Causal Models via Intentional Interventions","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2608.22765","title":"Learning to Control Coupled-Dynamics Environments with Joint Markov Decision Processes","created":"2026-08-24","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}