Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully
offline datasets. In addition to being conservative within the dataset, the generalization …

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 …

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience
with the outcomes achieved in that experience, and then imitate the relabeled experience …

Bimanual manipulation is important for building intelligent robots that unlock richer skills
than single arms. We consider a multi-object bimanual rearrangement task, where a …

As with any machine learning problem with limited data, effective offline RL algorithms
require careful regularization to avoid overfitting. One class of methods, known as one-step …

Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-
purpose policies from diverse and multi-task offline datasets. Despite notable recent …

While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its
algorithmic robustness, particularly against adversarial perturbations, remains unexplored …

Many applications of reinforcement learning can be formalized as goal-conditioned
environments, where, in each episode, there is a" goal" that affects the rewards obtained …

Model-based reinforcement learning is a promising learning strategy for practical robotic
applications due to its improved data-efficiency versus model-free counterparts. However …

Offline reinforcement learning (RL) aims to create policies for sequential decision-making
using exclusively offline datasets. This presents a significant challenge, especially when …