Reinforcement learning from human feedback (RLHF) can improve the quality of large
language model's (LLM) outputs by aligning them with human preferences. We propose a …

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets,
where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL …

Conservatism has led to significant progress in offline reinforcement learning (RL) where an
agent learns from pre-collected datasets. However, as many real-world scenarios involve …

Effective decision making involves flexibly relating past experiences and relevant contextual
information to a novel situation. In deep reinforcement learning (RL), the dominant paradigm …

StarCraft II is a challenging benchmark for AI agents due to the necessity of both precise
micro level operations and strategic macro awareness. Previous works, such as Alphastar …

Abstract The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent
Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre …

Deep neural networks are the most commonly used function approximators in offline
reinforcement learning. Prior works have shown that neural nets trained with TD-learning …

Diffusion models are a powerful class of generative models capable of mapping random
noise in high-dimensional spaces to a target manifold through iterative denoising. In this …

Abstract Monte Carlo Tree Search (MCTS) is a pronounced empirical search algorithm for
agent decision-making, especially when enhanced by Deep Learning (DL), in mastering …

Offline reinforcement learning (offline RL) is an emerging field that has recently begun
gaining attention across various application domains due to its ability to learn strategies from …