Can I read Implicit Distributional Reinforcement Learning on EtoBox?

Implicit Distributional Reinforcement Learning by Yue, Yuguang; Wang, Zhendong; Zhou, Mingyuan is a scholarly article available to read on EtoBox.

What is Implicit Distributional Reinforcement Learning about?

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. We adopt a distributional perspective on the discounted cumulative return and model it with a state-action-dependent implicit distribution, which is approximated by the DGNs that take state-action pairs and random noises as their input. Moreover, we use the SIA to provide a semi-implicit policy distribution, which mixes the policy parameters with a reparameterizable distribution that is not constrained by an analytic density function. In this way, the policy's marginal distribution is implicit, providing the potential to model complex properties such as covariance structure and skewness, but its parameter and entropy can still be estimated. We incorporate these features with an off-policy algorithm framework to solve problems with continuous action space and compare IDAC with state-of-the-art algorithms on representative OpenAI Gym environments. We observe that IDAC outperform

Author

Yue, Yuguang; Wang, Zhendong; Zhou, Mingyuan

Published

2020

Language

EN