Oracle-Guided Soft Shielding for Safe Move Prediction in Chess

TL;DR

This paper introduces Oracle-Guided Soft Shielding (OGSS), a framework that enhances safe decision-making in chess by combining probabilistic safety models with imitation learning, reducing tactical errors during exploration.

Contribution

The paper presents OGSS, a novel safety mechanism that integrates oracle feedback into imitation learning to improve safety and exploration in chess AI.

Findings

OGSS reduces blunder rates during exploration.

OGSS maintains safety while increasing exploration ratio.

OGSS outperforms existing safety methods in chess experiments.

Abstract

In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinforcement learning approaches for environments such as chess require hundreds of thousands of episodes and substantial computational resources to converge. Imitation learning, on the other hand, is more sample efficient but is brittle under distributional shift and lacks mechanisms for proactive risk avoidance. In this work, we propose Oracle-Guided Soft Shielding (OGSS), a simple yet effective framework for safer decision-making, enabling safe exploration by learning a probabilistic safety model from oracle feedback in an imitation learning setting. Focusing on the domain of chess, we train a model to predict strong moves based on past games, and separately learn a blunder prediction model from Stockfish evaluations to estimate the tactical risk of each move. During inference, the agent first generates a set of candidate moves and then uses the blunder model to determine high-risk options, and uses a utility function combining the predicted move likelihood from the policy model and the blunder probability to select actions that strike a balance between performance and safety. This enables the agent to explore and play competitively while significantly reducing the chance of tactical mistakes. Across hundreds of games against a strong chess engine, we compare our approach with other methods in the literature, such as action pruning, SafeDAgger, and uncertainty-based sampling. Our results demonstrate that OGSS variants maintain a lower blunder rate even as the agent's exploration ratio is increased by several folds, highlighting its ability to support broader exploration without compromising tactical soundness.