With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

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

Diffusion models are a class of flexible generative models trained with an approximation to
the log-likelihood objective. However, most use cases of diffusion models are not concerned …

In this work, we present a scalable reinforcement learning method for training multi-task
policies from large offline datasets that can leverage both human demonstrations and …

Nowadays, open-source large language models like LLaMA have emerged. Recent
developments have incorporated supervised fine-tuning (SFT) and reinforcement learning …

Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-
learning (IQL) addresses this by training a Q-function using only dataset actions through a …

Reinforcement learning (RL) provides a theoretical framework for continuously improving an
agent's behavior via trial and error. However, efficiently learning policies from scratch can be …

Guided sampling is a vital approach for applying diffusion models in real-world tasks that
embeds human-defined guidance during the sampling procedure. This paper considers a …

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the
environment. We aim to tackle a more challenging problem: learning a safe policy from an …

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional
policy produces promising results. The Decision Transformer (DT) combines the conditional …