{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"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":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144},{"id":"2203.09168","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","created":"2022-03-17","cited_by_count":120},{"id":"1711.08946","title":"Action Branching Architectures for Deep Reinforcement Learning","created":"2017-11-24","cited_by_count":92},{"id":"1712.00378","title":"Time Limits in Reinforcement Learning","created":"2017-12-01","cited_by_count":79},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"1901.10500","title":"Discretizing Continuous Action Space for On-Policy Optimization","created":"2019-01-29","cited_by_count":68},{"id":"1705.05035","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","created":"2017-05-14","cited_by_count":51},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38},{"id":"2001.08116","title":"Q-Learning in enormous action spaces via amortized approximate maximization","created":"2020-01-22","cited_by_count":30},{"id":"1906.12266","title":"Growing Action Spaces","created":"2019-06-28","cited_by_count":29},{"id":"1801.03326","title":"Expected Policy Gradients for Reinforcement Learning","created":"2018-01-10","cited_by_count":28},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24},{"id":"2010.14680","title":"Learning to Represent Action Values as a Hypergraph on the Action Vertices","created":"2020-10-28","cited_by_count":23},{"id":"1905.09855","title":"Distributional Policy Optimization: An Alternative Approach for Continuous Control","created":"2019-05-23","cited_by_count":22},{"id":"2011.07537","title":"Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking","created":"2020-11-15","cited_by_count":19},{"id":"1706.05374","title":"Expected Policy Gradients","created":"2017-06-15","cited_by_count":16},{"id":"1906.00572","title":"Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning","created":"2019-06-03","cited_by_count":16},{"id":"1709.00503","title":"Mean Actor Critic","created":"2017-09-01","cited_by_count":8},{"id":"1910.09093","title":"All-Action Policy Gradient Methods: A Numerical Integration Approach","created":"2019-10-21","cited_by_count":4},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","cited_by_count":4},{"id":"2207.01613","title":"Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions","created":"2022-07-04","cited_by_count":2},{"id":"2205.05588","title":"Characterizing the Action-Generalization Gap in Deep Q-Learning","created":"2022-05-11","cited_by_count":1}],"next_cursor":null}