Learning to Teach Reinforcement Learning Agents

July 28, 2017 Β· Declared Dead Β· πŸ› Machine Learning and Knowledge Extraction

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Anestis Fachantidis, Matthew E. Taylor, Ioannis Vlahavas arXiv ID 1707.09079 Category cs.AI: Artificial Intelligence Citations 60 Venue Machine Learning and Knowledge Extraction Last Checked 3 months ago
Abstract
In this article we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this setting, such as the average performance of the teacher, its variance and the importance of reward discounting in advising. The experiments show the non-trivial importance of the coefficient of variation (CV) as a statistic for choosing policies that generate advice. The CV statistic relates variance to the corresponding mean. Second, the article studies policy learning for distributing advice under a budget. Whereas most methods in the relevant literature rely on heuristics for advice distribution we formulate the problem as a learning one and propose a novel RL algorithm capable of learning when to advise, adapting to the student and the task at hand. Furthermore, we argue that learning to advise under a budget is an instance of a more generic learning problem: Constrained Exploitation Reinforcement Learning.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted