{"total":60,"rows":[{"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":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"area":"alignment"},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2110.12080","title":"C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks","created":"2021-10-22","cited_by_count":17,"area":null},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2206.03383","title":"On the Role of Discount Factor in Offline Reinforcement Learning","created":"2022-06-07","cited_by_count":16,"area":"offlinerl"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2209.13413","title":"Reinforcement Learning with Non-Exponential Discounting","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2102.04897","title":"Learning State Representations from Random Deep Action-conditional Predictions","created":"2021-02-09","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2204.01160","title":"Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs","created":"2022-04-03","cited_by_count":5,"area":null},{"id":"2204.12937","title":"Learning to Transfer Role Assignment Across Team Sizes","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2302.03608","title":"Online Reinforcement Learning with Uncertain Episode Lengths","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2304.05073","title":"A Tale of Sampling and Estimation in Discounted Reinforcement Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2302.05740","title":"UGAE: A Novel Approach to Non-exponential Discounting","created":"2023-02-11","cited_by_count":3,"area":null},{"id":"2305.18491","title":"Towards a Better Understanding of Representation Dynamics under TD-learning","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2510.16175","title":"The Formalism-Implementation Gap in Reinforcement Learning Research","created":"2025-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2604.17551","title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","created":"2026-04-19","cited_by_count":3,"area":"deeprl"},{"id":"2210.08569","title":"Limited or Biased: Modeling Sub-Rational Human Investors in Financial Markets","created":"2022-10-16","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":"2402.00787","title":"Learning and Calibrating Heterogeneous Bounded Rational Market Behaviour with Multi-Agent Reinforcement Learning","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2202.04224","title":"Intelligent Autonomous Intersection Management","created":"2022-02-09","cited_by_count":1,"area":null},{"id":"2205.01212","title":"Streaming Inference for Infinite Non-Stationary Clustering","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2602.04131","title":"Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting","created":"2026-02-04","cited_by_count":1,"area":"deeprl"},{"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":"2009.09577","title":"Learn to Exceed: Stereo Inverse Reinforcement Learning with Concurrent Policy Optimization","created":"2020-09-21","cited_by_count":0,"area":"offlinerl"},{"id":"2203.05782","title":"Overcoming Temptation: Incentive Design For Intertemporal Choice","created":"2022-03-11","cited_by_count":0,"area":null},{"id":"2208.05791","title":"Empirical investigations on WVA structural issues","created":"2022-08-11","cited_by_count":0,"area":null},{"id":"2210.05262","title":"Factors of Influence of the Overestimation Bias of Q-Learning","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2211.17012","title":"Correlation of the importances of neural network weights calculated by modern methods of overcoming catastrophic forgetting","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2212.14530","title":"POMRL: No-Regret Learning-to-Plan with Increasing Horizons","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2307.10491","title":"Markov Decision Processes with Time-Varying Geometric Discounting","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2309.12841","title":"Reward Function Design for Crowd Simulation via Reinforcement Learning","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2310.16655","title":"Towards Control-Centric Representations in Reinforcement Learning from Images","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2402.07462","title":"A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse?","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2411.14783","title":"Segmenting Action-Value Functions Over Time-Scales in SARSA via TD($\\Delta$)","created":"2024-11-22","cited_by_count":0,"area":"deeprl"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.31222","title":"Multivariate Distributional Reinforcement Learning Using Sliced Divergences","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.05194","title":"Temporal Preference Concepts and their Functions in a Large Language Model","created":"2026-05-11","cited_by_count":0,"area":"mechinterp"},{"id":"2607.20656","title":"Adaptive Multi-Horizon Reinforcement Learning","created":"2026-07-22","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}