English

Leveraging exploration in off-policy algorithms via normalizing flows

Machine Learning 2019-09-25 v3 Machine Learning

Abstract

The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches such as neural density models and continuous exploration (e.g., Go-Explore) have been proposed to maintain the high exploration rate necessary to find high performing and generalizable policies. Soft actor-critic(SAC) is another method for improving exploration that aims to combine efficient learning via off-policy updates while maximizing the policy entropy. In this work, we extend SAC to a richer class of probability distributions (e.g., multimodal) through normalizing flows (NF) and show that this significantly improves performance by accelerating the discovery of good policies while using much smaller policy representations. Our approach, which we call SAC-NF, is a simple, efficient,easy-to-implement modification and improvement to SAC on continuous control baselines such as MuJoCo and PyBullet Roboschool domains. Finally, SAC-NF does this while being significantly parameter efficient, using as few as 5.5% the parameters for an equivalent SAC model.

Keywords

Cite

@article{arxiv.1905.06893,
  title  = {Leveraging exploration in off-policy algorithms via normalizing flows},
  author = {Bogdan Mazoure and Thang Doan and Audrey Durand and R Devon Hjelm and Joelle Pineau},
  journal= {arXiv preprint arXiv:1905.06893},
  year   = {2019}
}

Comments

Accepted to 3rd Conference on Robot Learning (CoRL 2019); Keywords: Exploration, soft actor-critic, normalizing flow, off-policy; maximum entropy, reinforcement learning; deceptive reward; sparse reward; inverse autoregressive flow

R2 v1 2026-06-23T09:09:11.405Z