Reward Estimation for Variance Reduction in Deep Reinforcement Learning

Joshua Romoff, Peter Henderson, Alexandre Piché, Vincent François-Lavet, Joelle Pineau

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations


Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the reward with external factors that are not known to the agent. Corruption or stochasticity of the reward signal can be especially problematic in robotics, where goal specification can be particularly difficult for complex tasks. While many variance reduction techniques have been studied to improve the robustness of the RL process, handling such stochastic or corrupted reward structures remains difficult. As an alternative for handling this scenario in model-free RL methods, we suggest using an estimator for both rewards and value functions. We demonstrate that this improves performance under corrupted stochastic rewards in both the tabular and non-linear function approximation settings for a variety of noise types and environments. The use of reward estimation is a robust and easy-to-implement improvement for handling corrupted reward signals in model-free RL.

Original languageEnglish (US)
Pages (from-to)674-699
Number of pages26
JournalProceedings of Machine Learning Research
StatePublished - 2018
Externally publishedYes
Event2nd Conference on Robot Learning, CoRL 2018 - Zurich, Switzerland
Duration: Oct 29 2018Oct 31 2018

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


  • Goal Specification
  • Reinforcement Learning
  • Uncertainty


Dive into the research topics of 'Reward Estimation for Variance Reduction in Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this