Implicit Quantile Networks for Distributional Reinforcement Learning
By: Researcher
Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
| Authors | David Silver, Georg Ostrovski, Rémi Munos, Will Dabney |
| Journal/Conference Name | ICML 2018 7 |
| Paper Category | Artificial Intelligence |
| Paper Abstract | In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameterizing a distribution over the sample space, this yields an implicitly defined return distribution and gives rise to a large class of risk-sensitive policies. We demonstrate improved performance on the 57 Atari 2600 games in the ALE, and use our algorithm's implicitly defined distributions to study the effects of risk-sensitive policies in Atari games. |
| Date of publication | 2018 |
| Code Programming Language | Multiple |
| Comment |
Copyright Researcher 2022