Reward models trained on human preference data have been proven to effectively align
Large Language Models (LLMs) with human intent within the framework of reinforcement …

Navigation is one of the most heavily studied problems in robotics and is conventionally
approached as a geometric map** and planning problem. However, real-world navigation …

We propose a new policy representation based on score-based diffusion models (SDMs).
We apply our new policy representation in the domain of Goal-Conditioned Imitation …

Unsupervised pre-training has recently become the bedrock for computer vision and natural
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount
of offline data for complex decision-making tasks. Due to the distribution shift issue, current …

Given time series data, how can we answer questions like what will happen in the
future?''and how did we get here?''These sorts of probabilistic inference questions are …

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-
based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution …

While large-scale sequence modeling from offline data has led to impressive performance
gains in natural language and image generation, directly translating such ideas to robotics …

Offline reinforcement learning typically introduces a hierarchical structure to solve the long-
horizon problem so as to address its thorny issue of variance accumulation. Problems of …

We consider the problem of multi-objective alignment of foundation models with human
preferences, which is a critical step towards helpful and harmless AI systems. However, it is …