Scalable Online Planning via Reinforcement Learning Fine-Tuning
This addresses the problem of inefficient search in complex games for AI researchers and practitioners, representing a novel method rather than an incremental improvement.
The paper tackled the scalability limitations of tabular search methods in stochastic and partially observable environments by replacing them with online model-based fine-tuning of a policy neural network via reinforcement learning, achieving a new state-of-the-art result in self-play Hanabi and outperforming tabular search in Ms. Pacman.
Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular, we use our search algorithm to achieve a new state-of-the-art result in self-play Hanabi, and show the generality of our algorithm by also showing that it outperforms tabular search in the Atari game Ms. Pacman.