Timezone: »

Scalable Online Planning via Reinforcement Learning Fine-Tuning
Arnaud Fickinger · Hengyuan Hu · Brandon Amos · Stuart Russell · Noam Brown

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

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.

Author Information

Arnaud Fickinger (UC Berkeley)
Hengyuan Hu (Carnegie Mellon University)
Brandon Amos (Carnegie Mellon University)
Stuart Russell (UC Berkeley)
Noam Brown (Facebook AI Research)

More from the Same Authors