{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1806.10761","title":"Survey of multifidelity methods in uncertainty propagation, inference, and optimization","created":"2018-06-28","cited_by_count":142},{"id":"1906.08383","title":"Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies","created":"2019-06-19","cited_by_count":124},{"id":"1711.00123","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","created":"2017-10-31","cited_by_count":106},{"id":"1806.05618","title":"Stochastic Variance-Reduced Policy Gradient","created":"2018-06-14","cited_by_count":106},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"1301.2315","title":"The Optimal Reward Baseline for Gradient-Based Reinforcement Learning","created":"2013-01-10","cited_by_count":85},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"2110.05457","title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","created":"2021-10-11","cited_by_count":71},{"id":"1803.07246","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","created":"2018-03-20","cited_by_count":68},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60},{"id":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"1802.10031","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","created":"2018-02-27","cited_by_count":48},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38},{"id":"1703.01250","title":"Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization","created":"2017-03-03","cited_by_count":34},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25},{"id":"2410.20750","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","created":"2024-10-28","cited_by_count":25},{"id":"1905.03231","title":"Smoothing Policies and Safe Policy Gradients","created":"2019-05-08","cited_by_count":21},{"id":"2310.02902","title":"Searching for High-Value Molecules Using Reinforcement Learning and Transformers","created":"2023-10-04","cited_by_count":18},{"id":"1910.09066","title":"From Importance Sampling to Doubly Robust Policy Gradient","created":"2019-10-20","cited_by_count":17},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17},{"id":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17},{"id":"2008.01281","title":"Stochastic Grounded Action Transformation for Robot Learning in Simulation","created":"2020-08-04","cited_by_count":16},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16},{"id":"1908.03263","title":"Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods","created":"2019-08-08","cited_by_count":15},{"id":"2202.11170","title":"Multi-fidelity reinforcement learning framework for shape optimization","created":"2022-02-22","cited_by_count":9},{"id":"2402.10765","title":"Policy Learning for Off-Dynamics RL with Deficient Support","created":"2024-02-16","cited_by_count":9},{"id":"1811.06225","title":"Reward-estimation variance elimination in sequential decision processes","created":"2018-11-15","cited_by_count":4},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4},{"id":"1712.06489","title":"Multi-Fidelity Reinforcement Learning with Gaussian Processes","created":"2017-12-18","cited_by_count":2},{"id":"2107.04987","title":"Coordinate-wise Control Variates for Deep Policy Gradients","created":"2021-07-11","cited_by_count":1},{"id":"2411.10841","title":"Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment","created":"2024-11-16","cited_by_count":1}],"next_cursor":null}