M Janner, Q Li, S Levine - Advances in neural information …, 2021 - proceedings.neurips.cc
Reinforcement learning (RL) is typically viewed as the problem of estimating single-step policies (for model-free RL) or single-step models (for model-based RL), leveraging the …
Abstract Model-based reinforcement learning (RL) algorithms, which learn a dynamics model from logged experience and perform conservative planning under the learned model …
Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty …
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 …
N Hansen, X Wang, H Su - arXiv preprint arXiv:2203.04955, 2022 - arxiv.org
Data-driven model predictive control has two key advantages over model-free methods: a potential for improved sample efficiency through model learning, and better performance as …
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research …
In autonomous driving predicting future events in advance and evaluating the foreseeable risks empowers autonomous vehicles to plan their actions enhancing safety and efficiency …
YH Wu, X Wang, M Hamaya - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT …