Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
|||
| Line 1: | Line 1: | ||
= Introduction = | = Introduction = | ||
In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. | In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. This framework is a generalizes the typical machine learning set up using Markov Decision Processes. | ||
Revision as of 09:33, 12 March 2018
Introduction
In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. This framework is a generalizes the typical machine learning set up using Markov Decision Processes.