{"list":"other","total":104,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"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":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"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":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1702.02453","title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","created":"2017-02-08","cited_by_count":141},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"1509.01149","title":"Model Predictive Path Integral Control using Covariance Variable Importance Sampling","created":"2015-09-03","cited_by_count":124},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123},{"id":"1905.05217","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","created":"2019-05-13","cited_by_count":115},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"1611.01652","title":"A Differentiable Physics Engine for Deep Learning in Robotics","created":"2016-11-05","cited_by_count":108},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1404.3862","title":"Optimizing the CVaR via Sampling","created":"2014-04-15","cited_by_count":99},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"1609.05559","title":"Opponent Modeling in Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":97},{"id":"2002.04523","title":"Objective Mismatch in Model-based Reinforcement Learning","created":"2020-02-11","cited_by_count":96},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"id":"1804.07193","title":"Lipschitz Continuity in Model-based Reinforcement Learning","created":"2018-04-19","cited_by_count":91},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"2010.11876","title":"Error Bounds of Imitating Policies and Environments","created":"2020-10-22","cited_by_count":90},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"2011.09607","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","created":"2020-11-19","cited_by_count":87},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59},{"id":"1905.13320","title":"Combating the Compounding-Error Problem with a Multi-step Model","created":"2019-05-30","cited_by_count":54},{"id":"2008.12775","title":"On the model-based stochastic value gradient for continuous reinforcement learning","created":"2020-08-28","cited_by_count":47},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47},{"id":"2008.06622","title":"Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings","created":"2020-08-15","cited_by_count":42},{"id":"1501.05611","title":"Learning Contact-Rich Manipulation Skills with Guided Policy Search","created":"2015-01-22","cited_by_count":38},{"id":"2007.01995","title":"Bidirectional Model-based Policy Optimization","created":"2020-07-04","cited_by_count":38},{"id":"2010.04893","title":"Trust the Model When It Is Confident: Masked Model-based Actor-Critic","created":"2020-10-10","cited_by_count":36},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36},{"id":"2101.00531","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","created":"2021-01-02","cited_by_count":33},{"id":"2004.08763","title":"Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization","created":"2020-04-19","cited_by_count":32},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32},{"id":"1709.09480","title":"A Benchmark Environment Motivated by Industrial Control Problems","created":"2017-09-27","cited_by_count":31},{"id":"2004.11345","title":"Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads","created":"2020-04-23","cited_by_count":30},{"id":"2001.02792","title":"On Computation and Generalization of Generative Adversarial Imitation Learning","created":"2020-01-09","cited_by_count":28},{"id":"2101.06005","title":"SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning","created":"2021-01-15","cited_by_count":27},{"id":"2102.03483","title":"Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles","created":"2021-02-06","cited_by_count":27},{"id":"1910.04142","title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models","created":"2019-10-09","cited_by_count":26},{"id":"2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","created":"2021-05-31","cited_by_count":25},{"id":"2105.03363","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","created":"2021-05-07","cited_by_count":24},{"id":"1804.00379","title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning","created":"2018-04-02","cited_by_count":23},{"id":"2003.00030","title":"Policy-Aware Model Learning for Policy Gradient Methods","created":"2020-02-28","cited_by_count":23},{"id":"1803.10227","title":"Forward-Backward Reinforcement Learning","created":"2018-03-27","cited_by_count":19},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17},{"id":"2010.09546","title":"Model-based Policy Optimization with Unsupervised Model Adaptation","created":"2020-10-19","cited_by_count":16},{"id":"2105.06350","title":"MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks","created":"2021-05-13","cited_by_count":13},{"id":"2111.08550","title":"On Effective Scheduling of Model-based Reinforcement Learning","created":"2021-11-16","cited_by_count":13},{"id":"2206.04890","title":"Adversarial Counterfactual Environment Model Learning","created":"2022-06-10","cited_by_count":12},{"id":"1907.09278","title":"A Sufficient Statistic for Influence in Structured Multiagent Environments","created":"2019-07-22","cited_by_count":8},{"id":"2106.10424","title":"On Generalization of Adversarial Imitation Learning and Beyond","created":"2021-06-19","cited_by_count":7},{"id":"1807.09537","title":"Using control synthesis to generate corner cases: A case study on autonomous driving","created":"2018-07-25","cited_by_count":6}],"next_cursor":"100"}