CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement Learning

TL;DR

This paper introduces CIER, a novel method combining causal inference with experience replay in deep reinforcement learning to improve data efficiency and explainability, validated through experiments in standard environments.

Contribution

The paper presents a new approach that segments time series for causal analysis and integrates it into experience replay, enhancing DRL training effectiveness and interpretability.

Findings

Improved training efficiency in DRL environments.

Enhanced explainability of the training process.

Effective extension with priority experience replay.

Abstract

In the training process of Deep Reinforcement Learning (DRL), agents require repetitive interactions with the environment. With an increase in training volume and model complexity, it is still a challenging problem to enhance data utilization and explainability of DRL training. This paper addresses these challenges by focusing on the temporal correlations within the time dimension of time series. We propose a novel approach to segment multivariate time series into meaningful subsequences and represent the time series based on these subsequences. Furthermore, the subsequences are employed for causal inference to identify fundamental causal factors that significantly impact training outcomes. We design a module to provide feedback on the causality during DRL training. Several experiments demonstrate the feasibility of our approach in common environments, confirming its ability to enhance the effectiveness of DRL training and impart a certain level of explainability to the training process. Additionally, we extended our approach with priority experience replay algorithm, and experimental results demonstrate the continued effectiveness of our approach.