Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For un …
Y Ma, HAO Jianye, H Liang, C Xiao - Forty-first International …, 2023 - openreview.net
Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT …
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the …
Abstract Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a …
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action …
In reinforcement learning (RL), representation learning is a proven tool for complex image- based tasks, but is often overlooked for environments with low-level states, such as physical …
Y Wang, M Xu, L Shi, Y Chi - Uncertainty in Artificial …, 2023 - proceedings.mlr.press
Transformers hold tremendous promise in solving offline reinforcement learning (RL) by formulating it as a sequence modeling problem inspired by language modeling (LM). Prior …
D Ramani - arXiv preprint arXiv:1904.06736, 2019 - arxiv.org
Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent …
Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many …