S Fujimoto, SS Gu - Advances in neural information …, 2021 - proceedings.neurips.cc
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 …
CA Cheng, T Xie, N Jiang… - … Conference on Machine …, 2022 - proceedings.mlr.press
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 …
T Yamagata, A Khalil… - … on Machine Learning, 2023 - proceedings.mlr.press
Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional …