Advantage-weighted Regression: Simple And Scalable Off-policy Reinforcement Learning

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypeng2019advantage

Related papers

• Importance Weighted Policy Learning And Adaptation (2020)0.00
• A2PO: Towards Effective Offline Reinforcement Learning From An Advantage-aware Perspective (2024)1.69
• FAWAC: Feasibility Informed Advantage Weighted Regression For Persistent Safety In Offline Reinforcement Learning (2024)0.00
• Reward-weighted Regression Converges To A Global Optimum (2021)0.00
• Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-critic With Advantage Weighted Mixture Policy(sac-awmp) (2020)0.00
• Off-policy Reinforcement Learning With Loss Function Weighted By Temporal Difference Error (2022)2.26
• An Advantage Based Policy Transfer Algorithm For Reinforcement Learning With Measures Of Transferability (2023)0.00
• Offline Meta-reinforcement Learning With Advantage Weighting (2020)0.00