Counterfactual Credit Assignment in Model-Free Reinforcement Learning

by   Thomas Mesnard, et al.

Credit assignment in reinforcement learning is the problem of measuring an action influence on future rewards. In particular, this requires separating skill from luck, ie. 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 then propose to use these as future-conditional baselines and critics in policy gradient algorithms and we develop a valid, practical variant with provably lower variance, while achieving unbiasedness by constraining the hindsight information not to contain information about the agent actions. We demonstrate the efficacy and validity of our algorithm on a number of illustrative problems.


page 6

page 18


Towards Practical Credit Assignment for Deep Reinforcement Learning

Credit assignment is a fundamental problem in reinforcement learning, th...

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment

Many transfer problems require re-using previously optimal decisions for...

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning

How do we formalize the challenge of credit assignment in reinforcement ...

Learning Guidance Rewards with Trajectory-space Smoothing

Long-term temporal credit assignment is an important challenge in deep r...

On Credit Assignment in Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) has held longstanding promise ...

Synthetic Returns for Long-Term Credit Assignment

Since the earliest days of reinforcement learning, the workhorse method ...

Credit Assignment Techniques in Stochastic Computation Graphs

Stochastic computation graphs (SCGs) provide a formalism to represent st...