Reproduce “Exploration via Epistemic Value Estimation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Simon Schmitt, John Shawe-Taylor, Hado van Hasselt

EVE estimates uncertainty about expected returns to guide reinforcement-learning exploration. It models return distributions, approximates a Gaussian posterior over network parameters, and samples value functions for episode-level action selection and bootstrapped Q-learning targets. On 30×30 Deep Sea, the agent found treasure in more than 70% of episodes across 30 seeds, while DQN failed; this is a benchmark result, not a general guarantee.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.