Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

10/01/2019
by   Xue Bin Peng, et al.
0

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.

READ FULL TEXT

page 7

page 9

research
02/12/2021

Q-Value Weighted Regression: Reinforcement Learning with Limited Data

Sample efficiency and performance in the offline setting have emerged as...
research
02/19/2020

Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning

Off-policy reinforcement learning algorithms promise to be applicable in...
research
01/05/2019

Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization

Real-world tasks are often highly structured. Hierarchical reinforcement...
research
09/10/2015

Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies

This paper proposes GProp, a deep reinforcement learning algorithm for c...
research
03/16/2023

Goal-conditioned Offline Reinforcement Learning through State Space Partitioning

Offline reinforcement learning (RL) aims to infer sequential decision po...
research
02/23/2021

Greedy Multi-step Off-Policy Reinforcement Learning

Multi-step off-policy reinforcement learning has achieved great success....
research
01/18/2019

On-Policy Trust Region Policy Optimisation with Replay Buffers

Building upon the recent success of deep reinforcement learning methods,...

Please sign up or login with your details

Forgot password? Click here to reset