Automatic Goal Generation for Reinforcement Learning Agents

TL;DR

This paper introduces an adversarial training framework that enables reinforcement learning agents to automatically generate and learn a diverse set of tasks, creating an adaptive curriculum without prior environment knowledge.

Contribution

It proposes a novel generator network trained adversarially to produce appropriately challenging goals, facilitating automatic curriculum generation for multi-task reinforcement learning.

Findings

Agents can learn multiple tasks efficiently without prior environment knowledge.

The method effectively handles sparse reward scenarios.

Automatic task generation improves learning speed and diversity.

Abstract

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing. We use a generator network to propose tasks for the agent to try to achieve, specified as goal states. The generator network is optimized using adversarial training to produce tasks that are always at the appropriate level of difficulty for the agent. Our method thus automatically produces a curriculum of tasks for the agent to learn. We show that, by using this framework, an agent can efficiently and automatically learn to perform a wide set of tasks without requiring any prior knowledge of its environment. Our method can also learn to achieve tasks with sparse rewards, which traditionally pose significant challenges.