Building agents based on tree-search planning capabilities with learned models has
achieved remarkable success in classic decision-making problems, such as Go and Atari …

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in
JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and …

Simple regret is a natural and parameter-free performance criterion for pure exploration in
multi-armed bandits yet is less popular than the probability of missing the best arm or an …

Process synthesis in chemical engineering is a complex planning problem due to vast
search spaces, continuous parameters and the need for generalization. Deep reinforcement …

We propose a new approach to automated theorem proving where an AlphaZero-style agent
is self-training to refine a generic high-level expert strategy expressed as a nondeterministic …

Abstract Monte Carlo Tree Search (MCTS) algorithms such as AlphaGo and MuZero have
achieved superhuman performance in many challenging tasks. However, the computational …

We propose the Thinker algorithm, a novel approach that enables reinforcement learning
agents to autonomously interact with and utilize a learned world model. The Thinker …

Opponent modeling is a longstanding research topic aimed at enhancing decision-making
by modeling information about opponents in multi-agent environments. However, existing …

Abstract The application of Deep Reinforcement Learning (DRL) to inventory management
is an emerging field. However, traditional DRL algorithms, originally developed for diverse …

Evaluating deep multiagent reinforcement learning (MARL) algorithms is complicated by
stochasticity in training and sensitivity of agent performance to the behavior of other agents …