{"list":"other","total":56,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"2002.06487","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","created":"2020-02-16","cited_by_count":117},{"id":"1609.05559","title":"Opponent Modeling in Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":97},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"1902.06865","title":"Hyperbolic Discounting and Learning over Multiple Horizons","created":"2019-02-19","cited_by_count":60},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2006.04147","title":"Peer Collaborative Learning for Online Knowledge Distillation","created":"2020-06-07","cited_by_count":58},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28},{"id":"1806.01780","title":"Mix&Match - Agent Curricula for Reinforcement Learning","created":"2018-06-05","cited_by_count":27},{"id":"1712.07893","title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","created":"2017-12-21","cited_by_count":25},{"id":"1907.09597","title":"Agent Modeling as Auxiliary Task for Deep Reinforcement Learning","created":"2019-07-22","cited_by_count":14},{"id":"2006.07781","title":"Non-local Policy Optimization via Diversity-regularized Collaborative Exploration","created":"2020-06-14","cited_by_count":13},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13},{"id":"1907.10827","title":"Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning","created":"2019-07-24","cited_by_count":11},{"id":"2012.04839","title":"Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation","created":"2020-12-09","cited_by_count":10},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8},{"id":"2111.09159","title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","created":"2021-11-17","cited_by_count":7},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6},{"id":"2203.01004","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","created":"2022-03-02","cited_by_count":3},{"id":"2002.00149","title":"Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning","created":"2020-02-01","cited_by_count":2},{"id":"2002.02202","title":"Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach","created":"2020-02-06","cited_by_count":2},{"id":"2002.05229","title":"Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing","created":"2020-02-12","cited_by_count":2},{"id":"2007.08229","title":"Mixture of Step Returns in Bootstrapped DQN","created":"2020-07-16","cited_by_count":2},{"id":"2206.00113","title":"BRExIt: On Opponent Modelling in Expert Iteration","created":"2022-05-31","cited_by_count":2},{"id":"1908.02269","title":"Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning","created":"2019-08-06","cited_by_count":1}],"next_cursor":null}