paper-with-me

홈 › Papers

Relative Entropy Regularized Policy Iteration

2018-12-05 · Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave, Steven Bohez, Yuval Tassa, Dan Belov, Nicolas Heess, Martin Riedmiller

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function; ii) policy improvement via the estimation of a local non-parametric policy; and iii) generalization by fitting a parametric policy. Each step can be implemented in different ways, giving rise to several algorithm variants. Our algorithm draws on connections to existing literature on black-box optimization and 'RL as an inference' and it can be seen either as an extension of the Maximum a Posteriori Policy Optimisation algorithm (MPO) [Abdolmaleki et al., 2018a], or as an extension of Trust Region Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) [Abdolmaleki et al., 2017b; Hansen et al., 1997] to a policy iteration scheme. Our comparison on 31 continuous control tasks from parkour suite [Heess et al., 2017], DeepMind control suite [Tassa et al., 2018] and OpenAI Gym [Brockman et al., 2016] with diverse properties, limited amount of compute and a single set of hyperparameters, demonstrate the effectiveness of our method and the state of art results. Videos, summarizing results, can be found at goo.gl/HtvJKR .

📄 PDF Abstract BibTeX arXiv:1812.02256

Code (1)

acyclics/MPO pytorch

Tasks

continuous-controlContinuous ControlOpenAI GymReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis

2025-06-14 · Jihoon Suh, Yeongjun Jang, Kaoru Teranishi, Takashi Tanaka

We propose an efficient encrypted policy synthesis to develop privacy-preserving model-based reinforcement learning. We first demonstrate that the relative-entropy-regularized reinforcement learning framework offers a co…

Model-based Reinforcement LearningPrivacy PreservingQuantizationreinforcement-learning+1

FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching

2026-02-13 · Lei Lv, Yunfei Li, Yu Luo, Fuchun Sun 외 arxiv

Iterative generative policies, such as diffusion models and flow matching, offer superior expressivity for continuous control but complicate Maximum Entropy Reinforcement Learning because their action log-densities are n…

Reinforcement LearningContinuous ControlDensity Estimation

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

2023-10-11 · Zeyang Li, Chuxiong Hu, Yunan Wang, Guojian Zhan 외

Regularization is one of the most important techniques in reinforcement learning algorithms. The well-known soft actor-critic algorithm is a special case of regularized policy iteration where the regularizer is chosen as…

On the Convergence of Approximate and Regularized Policy Iteration Schemes

2019-09-20 · Elena Smirnova, Elvis Dohmatob

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifie…

Q-LearningReinforcement LearningReinforcement Learning (RL)

A Theory of Regularized Markov Decision Processes

2019-01-31 · Matthieu Geist, Bruno Scherrer, Olivier Pietquin

Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes …

Deep Reinforcement LearningQ-LearningReinforcement Learning