Advantage Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can accommodate continuous and discrete actions, and can be implemented in just a few lines of code on top of standard supervised learning methods. We provide a theoretical motivation for AWR and analyze its properties when incorporating off-policy data from experience replay. We evaluate AWR on a suite of standard OpenAI Gym benchmark tasks, and show that it achieves competitive performance compared to a number of well-established state-of-the-art RL algorithms. AWR is also able to acquire more effective policies than most off-policy algorithms when learning from purely static datasets with no additional environmental interactions. Furthermore, we demonstrate our algorithm on challenging continuous control tasks with highly complex simulated characters.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlOpenAI Gymregressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent max…
continuous-controlContinuous ControlOpenAI Gymregression+3CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization
Offline reinforcement learning (offline RL) algorithms often require additional constraints or penalty terms to address distribution shift issues, such as adding implicit or explicit policy constraints during policy opti…
D4RLOffline RLregressionQ-Value Weighted Regression: Reinforcement Learning with Limited Data
Sample efficiency and performance in the offline setting have emerged as significant challenges of deep reinforcement learning. We introduce Q-Value Weighted Regression (QWR), a simple RL algorithm that excels in these a…
Atari Gamescontinuous-controlContinuous ControlDeep Reinforcement Learning+6Hellinger Distance Constrained Regression
This paper introduces the off-policy reinforcement learning method that uses the Hellinger distance between sampling policy and current policy as a constraint. Hellinger distance squared multiplied by two is greater than…
MuJoCoregressionReinforcement Learning (RL)FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challenge is balancing safety and performance,…