Knows what it knows: a framework for self-aware learning

Authors:
Lihong Li;Michael L. Littman;Thomas J. Walsh;Alexander L. Strehl
Affiliations:
Yahoo! Research, Santa Clara, USA 95054;Department of Computer Science, Rutgers University, Piscataway, USA 08854;Department of Computer Science, University of Arizona, Tucson, USA 85721;Facebook, Palo Alto, USA 94304
Venue:
Machine Learning
Year:
2011

Citing 0
Cited 3

Handling ambiguous effects in action learning

EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
V-MAX: tempered optimism for better PAC reinforcement learning

Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Exploration in relational domains for model-based reinforcement learning

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a learning framework that combines elements of the well-known PAC and mistake-bound models. The KWIK (knows what it knows) framework was designed particularly for its utility in learning settings where active exploration can impact the training examples the learner is exposed to, as is true in reinforcement-learning and active-learning problems. We catalog several KWIK-learnable classes as well as open problems, and demonstrate their applications in experience-efficient reinforcement learning.