{"total":26,"rows":[{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2104.10190","title":"Outcome-Driven Reinforcement Learning via Variational Inference","created":"2021-04-20","cited_by_count":17,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2212.04407","title":"Dynamic Decision Frequency with Continuous Options","created":"2022-12-06","cited_by_count":13,"area":null},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"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":"2205.08464","title":"Robust Losses for Learning Value Functions","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2306.11208","title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2106.00922","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task","created":"2021-06-02","cited_by_count":2,"area":null},{"id":"2201.09653","title":"The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning","created":"2022-01-24","cited_by_count":2,"area":null},{"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":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"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":"2505.00913","title":"Fine-Tuning without Performance Degradation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2608.21501","title":"Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}