Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
Not on the map. Why?
Abstract (arXiv)
We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the efficiency of sample reuse, addressing a trade-off between two important deployment requirements for real-world control: (i) practical performance guarantees and (ii) data efficiency. We demonstrate the benefits of this new class of algorithms through extensive experimental analysis on a broad range of simulated control tasks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 28 Jun 2022.
Builds on
37 of 53 references.
References · 37
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2015Trust Region Policy Optimizationcited by 2,580
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
- 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
- 2015Prioritized Experience Replaycited by 1,099
- 2017Constrained Policy Optimizationcited by 983
- 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
- 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
- 2017Deep Reinforcement Learning that Matterscited by 754
25 more
- 2019Behavior Regularized Offline Reinforcement Learningcited by 662
- 2020MOReL : Model-Based Offline Reinforcement Learningcited by 590
- 2020dm_control: Software and Tasks for Continuous Controlcited by 375
- 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
- 2018Maximum a Posteriori Policy Optimisationcited by 328
- 2018Model-Ensemble Trust-Region Policy Optimizationcited by 219
- 2016Sample Efficient Actor-Critic with Experience Replaycited by 188
- 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
- 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 151
- 2019V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Controlcited by 85
- 2016Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Criticcited by 81
- 2019Safe Policies for Reinforcement Learning via Primal-Dual Methodscited by 79
- 2020A Game Theoretic Framework for Model Based Reinforcement Learningcited by 73
- 2019Truly Proximal Policy Optimizationcited by 69
- 2018Diversity-Driven Exploration Strategy for Deep Reinforcement Learningcited by 65
- 2018Remember and Forget for Experience Replaycited by 43
- 2017Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learningcited by 40
- 2021Generalized Proximal Policy Optimization with Sample Reusecited by 40
- 2019P3O: Policy-on Policy-off Policy Optimizationcited by 37
- 2019Trust Region-Guided Proximal Policy Optimizationcited by 36
- 2019Probabilistic model predictive safety certification for learning-based controlcited by 22
- 2022Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robotscited by 17
- 2018Supervised Policy Update for Deep Reinforcement Learningcited by 11
- 2020Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approachcited by 6
Built on by
Citing papers per year: 2023: 1.
1 paper.