Learning Retrospective Knowledge with Reverse Reinforcement Learning

Abstract

We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representing predictive knowledge, i.e., answering questions about possible future outcomes such as "how much fuel will be consumed in expectation if we drive from A to B?". GVFs, however, cannot answer questions like "how much fuel do we expect a car to have given it is at B at time $t$?". To answer this question, we need to know when that car had a full tank and how that car came to B. Since such questions emphasize the influence of possible past events on the present, we refer to their answers as retrospective knowledge. In this paper, we show how to represent retrospective knowledge with Reverse GVFs, which are trained via Reverse RL. We demonstrate empirically the utility of Reverse GVFs in both representation learning and anomaly detection.

arXiv commentNeurIPS 2020

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• A Simple Framework for Contrastive Learning of Visual Representations
• Addressing Function Approximation Error in Actor-Critic Methods
• Deep Learning for Anomaly Detection: A Survey
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• A Distributional Perspective on Reinforcement Learning
• DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
• When to use parametric models in reinforcement learning?
• On Convergence of Emphatic Temporal-Difference Learning
• GenDICE: Generalized Offline Estimation of Stationary Values
• An Analysis of Categorical Distributional Reinforcement Learning
• Consistent On-Line Off-Policy Evaluation
• Discovery of Useful Questions as Auxiliary Tasks
• Recall Traces: Backtracking Models for Efficient Reinforcement Learning
• Generative predecessor models for sample-efficient imitation learning
• Reinforcement Ranking
• Forethought and Hindsight in Credit Assignment