Hindsight Credit Assignment

Abstract

We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rather than employing foresight. Somewhat surprisingly, we show that value functions can be rewritten through this lens, yielding a new family of algorithms. We study the properties of these algorithms, and empirically show that they successfully address important credit assignment challenges, through a set of illustrative tasks.

NeurIPS 2019

Cited by in corpus (11)

• Agent57: Outperforming the Atari Human Benchmark
• Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving
• Training Agents using Upside-Down Reinforcement Learning
• Counterfactual Credit Assignment in Model-Free Reinforcement Learning
• Learning Guidance Rewards with Trajectory-space Smoothing
• Learning Long-Term Reward Redistribution via Randomized Return Decomposition
• An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning
• Preferential Temporal Difference Learning
• Value-driven Hindsight Modelling
• Policy Gradients Incorporating the Future
• Variance Reduced Advantage Estimation with $\delta$ Hindsight Credit Assignment