{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"2002.04504","title":"pymoo: Multi-objective Optimization in Python","created":"2020-01-22","cited_by_count":200},{"id":"2007.06700","title":"Revisiting Fundamentals of Experience Replay","created":"2020-07-13","cited_by_count":175},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2001.11231","title":"Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles","created":"2020-01-30","cited_by_count":110},{"id":"1810.05762","title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","created":"2018-10-12","cited_by_count":90},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63},{"id":"1810.01222","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","created":"2018-10-02","cited_by_count":58},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"2005.05719","title":"Smooth Exploration for Robotic Reinforcement Learning","created":"2020-05-12","cited_by_count":54},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51},{"id":"2007.02040","title":"Discount Factor as a Regularizer in Reinforcement Learning","created":"2020-07-04","cited_by_count":45},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45},{"id":"1701.00879","title":"PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization","created":"2017-01-04","cited_by_count":41},{"id":"1911.05892","title":"Reinforcement Learning for Market Making in a Multi-agent Dealer Market","created":"2019-11-14","cited_by_count":39},{"id":"1905.07628","title":"Evolving Rewards to Automate Reinforcement Learning","created":"2019-05-18","cited_by_count":31},{"id":"2305.12127","title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","created":"2023-05-20","cited_by_count":29},{"id":"1802.08842","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","created":"2018-02-24","cited_by_count":28},{"id":"1906.09807","title":"Proximal Distilled Evolutionary Reinforcement Learning","created":"2019-06-24","cited_by_count":27},{"id":"1907.02908","title":"On Inductive Biases in Deep Reinforcement Learning","created":"2019-07-05","cited_by_count":24},{"id":"2203.14009","title":"Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey","created":"2022-03-26","cited_by_count":23},{"id":"2301.12457","title":"EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation","created":"2023-01-29","cited_by_count":18},{"id":"2308.03665","title":"QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration","created":"2023-08-07","cited_by_count":17},{"id":"2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","created":"2021-07-03","cited_by_count":16},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14},{"id":"2006.07554","title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","created":"2020-06-13","cited_by_count":11},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10},{"id":"2302.12600","title":"EvoTorch: Scalable Evolutionary Computation in Python","created":"2023-02-24","cited_by_count":9},{"id":"2406.11905","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","created":"2024-06-15","cited_by_count":8},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7},{"id":"2206.08888","title":"Fast Population-Based Reinforcement Learning on a Single Machine","created":"2022-06-17","cited_by_count":7},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5},{"id":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","cited_by_count":4},{"id":"2404.08233","title":"Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning","created":"2024-04-12","cited_by_count":4},{"id":"2201.09568","title":"Pearl: Parallel Evolutionary and Reinforcement Learning Library","created":"2022-01-24","cited_by_count":3}],"next_cursor":null}