151. DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
- Author
-
Liang, Anthony, Tennenholtz, Guy, Hsu, Chih-wei, Chow, Yinlam, Bıyık, Erdem, and Boutilier, Craig
- Subjects
Computer Science - Machine Learning - 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 and simulated robot assistive tasks, demonstrating that DynaMITE-RL significantly outperforms state-of-the-art baselines in sample efficiency and inference returns. more...
- Published
- 2024