{"total":55,"rows":[{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242,"area":"alignment"},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96,"area":"wm"},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2212.03201","title":"Misspecification in Inverse Reinforcement Learning","created":"2022-12-06","cited_by_count":27,"area":"offlinerl"},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13,"area":"offlinerl"},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2302.11996","title":"K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2406.01793","title":"Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning","created":"2024-06-03","cited_by_count":6,"area":"offlinerl"},{"id":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"area":"offlinerl"},{"id":"2406.03812","title":"How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach","created":"2024-06-06","cited_by_count":5,"area":"offlinerl"},{"id":"2502.04403","title":"Agency Is Frame-Dependent","created":"2025-02-06","cited_by_count":5,"area":"deeprl"},{"id":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"area":"offlinerl"},{"id":"2208.09570","title":"Calculus on MDPs: Potential Shaping as a Gradient","created":"2022-08-20","cited_by_count":4,"area":null},{"id":"2210.14972","title":"Environment Design for Inverse Reinforcement Learning","created":"2022-10-26","cited_by_count":4,"area":"offlinerl"},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2403.06854","title":"Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification","created":"2024-03-11","cited_by_count":4,"area":"offlinerl"},{"id":"2406.18033","title":"Boosting Soft Q-Learning by Bounding","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2411.15046","title":"On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning","created":"2024-11-22","cited_by_count":4,"area":"offlinerl"},{"id":"2410.23680","title":"Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment","created":"2024-10-31","cited_by_count":3,"area":"offlinerl"},{"id":"2501.00989","title":"Bootstrapped Reward Shaping","created":"2025-01-02","cited_by_count":3,"area":"deeprl"},{"id":"2502.03762","title":"Learning Reward Machines from Partially Observed Policies","created":"2025-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2308.08427","title":"Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2312.09983","title":"Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping","created":"2023-12-15","cited_by_count":2,"area":"offlinerl"},{"id":"2501.01669","title":"Inversely Learning Transferable Rewards via Abstracted States","created":"2025-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2508.00159","title":"Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.07400","title":"Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2509.12010","title":"Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids","created":"2025-09-15","cited_by_count":1,"area":"offlinerl"},{"id":"2605.14599","title":"Fast Rates for Inverse Reinforcement Learning","created":"2026-05-14","cited_by_count":1,"area":"offlinerl"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2302.09676","title":"Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2306.01731","title":"PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward","created":"2023-06-02","cited_by_count":0,"area":"offlinerl"},{"id":"2403.14593","title":"Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof","created":"2024-03-21","cited_by_count":0,"area":"offlinerl"},{"id":"2405.15509","title":"Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2409.18051","title":"Inverse Reinforcement Learning with Multiple Planning Horizons","created":"2024-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2410.07643","title":"On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory","created":"2024-10-10","cited_by_count":0,"area":"offlinerl"},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2505.17249","title":"Where You Go is Who You Are: Behavioral Theory-Guided LLMs for Inverse Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.06956","title":"Statistical analysis of Inverse Entropy-regularized Reinforcement Learning","created":"2025-12-07","cited_by_count":0,"area":"offlinerl"},{"id":"2602.02912","title":"Notes on the Reward Representation of Posterior Updates","created":"2026-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2604.07480","title":"Active Reward Machine Inference From Raw State Trajectories","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.09217","title":"Learning the Preferences of a Learning Agent","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.22056","title":"Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning","created":"2026-06-20","cited_by_count":0,"area":"offlinerl"},{"id":"2608.08240","title":"A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.16888","title":"Q-based Variational Inverse Reinforcement Learning","created":"2026-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2609.13469","title":"Inverse Learning of the Altruism and Cost Level in Mixed-Individual Mean Field Games","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.00758","title":"Scalable Multi-Task Inverse Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}