Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning

TL;DR

This paper introduces a framework that uses generative adversarial imitation learning with external memory modules to learn complex, multi-step strategies in human decision making, improving long-term planning and policy learning.

Contribution

It proposes a novel memory-augmented imitation learning framework that captures subtask dependencies and task-level strategies, enhancing learning from complex demonstrations.

Findings

Successfully learned expert policies in autonomous highway driving

Outperformed state-of-the-art imitation learning methods

Effectively modeled subtask relationships and task-level strategies

Abstract

This paper presents a novel framework for automatic learning of complex strategies in human decision making. The task that we are interested in is to better facilitate long term planning for complex, multi-step events. We observe temporal relationships at the subtask level of expert demonstrations, and determine the different strategies employed in order to successfully complete a task. To capture the relationship between the subtasks and the overall goal, we utilise two external memory modules, one for capturing dependencies within a single expert demonstration, such as the sequential relationship among different sub tasks, and a global memory module for modelling task level characteristics such as best practice employed by different humans based on their domain expertise. Furthermore, we demonstrate how the hidden state representation of the memory can be used as a reward signal to smooth the state transitions, eradicating subtle changes. We evaluate the effectiveness of the proposed model for an autonomous highway driving application, where we demonstrate its capability to learn different expert policies and outperform state-of-the-art methods. The scope in industrial applications extends to any robotics and automation application which requires learning from complex demonstrations containing series of subtasks.