Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Abstract
Credit assignment in reinforcement learning is the problem of measuring an action’s influence on future rewards. In particular, this requires separating skill from luck, i.e. disentangling the effect of an action on rewards from that of external factors and subsequent actions. To achieve this, we adapt the notion of counterfactuals from causality theory to a model-free RL setup. The key idea is to condition value functions on future events, by learning to extract relevant information from a trajectory. We formulate a family of policy gradient algorithms that use these future-conditional value functions as baselines or critics, and show that they are provably low variance. To avoid the potential bias from conditioning on future information, we constrain the hindsight information to not contain information about the agent’s actions. We demonstrate the efficacy and validity of our algorithm on a number of illustrative and challenging problems.
Cite
Text
Mesnard et al. "Counterfactual Credit Assignment in Model-Free Reinforcement Learning." International Conference on Machine Learning, 2021.Markdown
[Mesnard et al. "Counterfactual Credit Assignment in Model-Free Reinforcement Learning." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/mesnard2021icml-counterfactual/)BibTeX
@inproceedings{mesnard2021icml-counterfactual,
title = {{Counterfactual Credit Assignment in Model-Free Reinforcement Learning}},
author = {Mesnard, Thomas and Weber, Theophane and Viola, Fabio and Thakoor, Shantanu and Saade, Alaa and Harutyunyan, Anna and Dabney, Will and Stepleton, Thomas S and Heess, Nicolas and Guez, Arthur and Moulines, Eric and Hutter, Marcus and Buesing, Lars and Munos, Remi},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {7654-7664},
volume = {139},
url = {https://mlanthology.org/icml/2021/mesnard2021icml-counterfactual/}
}