Random Latent Exploration for Deep Reinforcement Learning

TL;DR

This paper presents Random Latent Exploration (RLE), a novel exploration strategy for reinforcement learning that samples goals in a latent space, outperforming traditional noise and bonus-based methods across various tasks.

Contribution

RLE introduces a simple, effective exploration method that leverages latent space sampling, improving RL performance without complex bonus calculations.

Findings

RLE outperforms noise-based exploration methods.

RLE improves performance on Atari and continuous control tasks.

RLE is a simple, plug-in exploration strategy.

Abstract

We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which rewards the agent for attempting novel behaviors. The core idea of RLE is to encourage the agent to explore different parts of the environment by pursuing randomly sampled goals in a latent space. RLE is as simple as noise-based methods, as it avoids complex bonus calculations but retains the deep exploration benefits of bonus-based methods. Our experiments show that RLE improves performance on average in both discrete (e.g., Atari) and continuous control tasks (e.g., Isaac Gym), enhancing exploration while remaining a simple and general plug-in for existing RL algorithms. Project website and code: https://srinathm1359.github.io/random-latent-exploration