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

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data.
Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms …

Imitating human demonstrations is a promising approach to endow robots with various
manipulation capabilities. While recent advances have been made in imitation learning and …

Abstract We propose Adversarially Trained Actor Critic (ATAC), a new model-free algorithm
for offline reinforcement learning (RL) under insufficient data coverage, based on the …

Offline reinforcement learning (RL) aims to find performant policies from logged data without
further environment interaction. Model-based algorithms, which learn a model of the …

Recent work has shown that supervised learning alone, without temporal difference (TD)
learning, can be remarkably effective for offline RL. When does this hold true, and which …

Recent advance in deep offline reinforcement learning (RL) has made it possible to train
strong robotic agents from offline datasets. However, depending on the quality of the trained …

Deep reinforcement learning (RL) has led to many recent and groundbreaking advances.
However, these advances have often come at the cost of both increased scale in the …

Reinforcement learning (RL) has been shown to have the potential for optimal control of
heating, ventilation, and air conditioning (HVAC) systems. Although research on RL-based …

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