all AI news
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Feb. 27, 2024, 5:41 a.m. | Anthony Liang, Guy Tennenholtz, Chih-wei Hsu, Yinlam Chow, Erdem B{\i}y{\i}k, Craig Boutilier
cs.LG updates on arXiv.org arxiv.org
Abstract: We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episode sessions - parts of the episode where the latent state is fixed - and propose three key modifications to existing meta-RL methods: consistency of latent information within sessions, session masking, and prior latent conditioning. We demonstrate the importance of these modifications in various domains, ranging from discrete Gridworld environments to continuous-control …
abstract approximate inference arxiv cs.lg dynamic environments inference key meta reinforcement reinforcement learning state temporal type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Codec Avatars Research Engineer
@ Meta | Pittsburgh, PA