Learning to Reach Goals via Iterated Supervised Learning

TL;DR

This paper introduces an iterative supervised learning algorithm enabling agents to learn goal-reaching behaviors from scratch without expert demonstrations, improving robustness and performance in sparse reward environments.

Contribution

It proposes a novel RL method that relabels and imitates its own trajectories, eliminating the need for demonstrations or value functions, with theoretical performance guarantees.

Findings

Improved goal-reaching performance over existing RL algorithms

Enhanced robustness in benchmark tasks

Theoretical bounds on policy performance

Abstract

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study RL algorithms that use imitation learning to acquire goal reaching policies from scratch, without the need for expert demonstrations or a value function. In lieu of demonstrations, we leverage the property that any trajectory is a successful demonstration for reaching the final state in that same trajectory. We propose a simple algorithm in which an agent continually relabels and imitates the trajectories it generates to progressively learn goal-reaching behaviors from scratch. Each iteration, the agent collects new trajectories using the latest policy, and maximizes the likelihood of the actions along these trajectories under the goal that was actually reached, so as to improve the policy. We formally show that this iterated supervised learning procedure optimizes a bound on the RL objective, derive performance bounds of the learned policy, and empirically demonstrate improved goal-reaching performance and robustness over current RL algorithms in several benchmark tasks.