{"list":"other","total":56,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"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":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"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":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"2009.14471","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","created":"2020-09-30","cited_by_count":220},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"2103.04931","title":"Monte Carlo Tree Search: A Review of Recent Modifications and Applications","created":"2021-03-08","cited_by_count":161},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"1606.02960","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","created":"2016-06-09","cited_by_count":127},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"1511.04143","title":"Deep Reinforcement Learning in Parameterized Action Space","created":"2015-11-13","cited_by_count":68},{"id":"1901.10500","title":"Discretizing Continuous Action Space for On-Policy Optimization","created":"2019-01-29","cited_by_count":68},{"id":"1801.10395","title":"Probabilistic Recurrent State-Space Models","created":"2018-01-31","cited_by_count":64},{"id":"1902.10565","title":"Accelerating Self-Play Learning in Go","created":"2019-02-27","cited_by_count":64},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48},{"id":"1805.11593","title":"Observe and Look Further: Achieving Consistent Performance on Atari","created":"2018-05-29","cited_by_count":44},{"id":"2109.05490","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","created":"2021-09-12","cited_by_count":35},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17},{"id":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8}],"next_cursor":null}