{"list":"other","total":51,"rows":[{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1806.07857","title":"RUDDER: Return Decomposition for Delayed Rewards","created":"2018-06-20","cited_by_count":173},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"2002.04083","title":"Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations","created":"2020-02-10","cited_by_count":155},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"1506.05254","title":"Gradient Estimation Using Stochastic Computation Graphs","created":"2015-06-17","cited_by_count":121},{"id":"1912.02877","title":"Training Agents using Upside-Down Reinforcement Learning","created":"2019-12-05","cited_by_count":107},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"1912.02503","title":"Hindsight Credit Assignment","created":"2019-12-05","cited_by_count":79},{"id":"1803.07246","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","created":"2018-03-20","cited_by_count":68},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"1810.06721","title":"Optimizing Agent Behavior over Long Time Scales by Transporting Value","created":"2018-10-15","cited_by_count":58},{"id":"1806.03107","title":"Temporal Difference Variational Auto-Encoder","created":"2018-06-08","cited_by_count":49},{"id":"1802.10031","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","created":"2018-02-27","cited_by_count":48},{"id":"1906.07073","title":"Is the Policy Gradient a Gradient?","created":"2019-06-17","cited_by_count":40},{"id":"2008.06036","title":"Reinforcement Learning with Trajectory Feedback","created":"2020-08-13","cited_by_count":40},{"id":"1711.06006","title":"Hindsight policy gradients","created":"2017-11-16","cited_by_count":37},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37},{"id":"2009.14108","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","created":"2020-09-29","cited_by_count":36},{"id":"1809.03702","title":"Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding","created":"2018-09-11","cited_by_count":34},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33},{"id":"2007.01839","title":"Expected Eligibility Traces","created":"2020-07-03","cited_by_count":27},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27},{"id":"1804.00379","title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning","created":"2018-04-02","cited_by_count":23},{"id":"1706.06643","title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines","created":"2017-06-20","cited_by_count":20},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20},{"id":"1901.01761","title":"Credit Assignment Techniques in Stochastic Computation Graphs","created":"2019-01-07","cited_by_count":14},{"id":"2011.01298","title":"Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models","created":"2020-11-02","cited_by_count":14},{"id":"2002.08329","title":"Value-driven Hindsight Modelling","created":"2020-02-19","cited_by_count":6},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6},{"id":"2106.04499","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":5},{"id":"2105.00568","title":"InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem","created":"2021-05-02","cited_by_count":2},{"id":"1911.08362","title":"Variance Reduced Advantage Estimation with $\\delta$ Hindsight Credit Assignment","created":"2019-11-19","cited_by_count":1}],"next_cursor":null}