Keywords: reinforcement learning, exploration, generalization, contextual MDP
TL;DR: Propose a new algorithm for exploration in contextual MDPs where the environment changes each episode; new SOTA results on MiniHack, outperform existing methods for reward-free exploration on Habitat.
Abstract: In recent years, a number of reinforcement learning (RL) methods have been pro- posed to explore complex environments which differ across episodes. In this work, we show that the effectiveness of these methods critically relies on a count-based episodic term in their exploration bonus. As a result, despite their success in relatively simple, noise-free settings, these methods fall short in more realistic scenarios where the state space is vast and prone to noise. To address this limitation, we introduce Exploration via Elliptical Episodic Bonuses (E3B), a new method which extends count-based episodic bonuses to continuous state spaces and encourages an agent to explore states that are diverse under a learned embed- ding within each episode. The embedding is learned using an inverse dynamics model in order to capture controllable aspects of the environment. Our method sets a new state-of-the-art across 16 challenging tasks from the MiniHack suite, without requiring task-specific inductive biases. E3B also outperforms existing methods in reward-free exploration on Habitat, demonstrating that it can scale to high-dimensional pixel-based observations and realistic environments.
Supplementary Material: zip