A formal theory of plan recognition and its implementation
Reasoning about plans
A Bayesian model of plan recognition
Artificial Intelligence
Creating advice-taking reinforcement learners
Machine Learning - Special issue on reinforcement learning
Abstraction and approximate decision-theoretic planning
Artificial Intelligence
Automated assistants to aid humans in understanding team behaviors
AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
TTree: Tree-Based State Generalization with Temporally Abstract Actions
Proceedings of the 5th International Symposium on Abstraction, Reformulation and Approximation
Automated Advice-Giving Strategies for Scientific Inquiry
ITS '96 Proceedings of the Third International Conference on Intelligent Tutoring Systems
The RoboCup synthetic agent challenge 97
IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
An MDP-based recommender system
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
CommLang: communication for coachable agents
RoboCup 2004
Hi-index | 0.01 |
An advising agent, a coach, provides advice to other agents about how to act. In this paper we contribute an advice generation method using observations of agents acting in an environment. Given an abstract state definition and partially specified abstract actions, the algorithm extracts a Markov Chain, infers a Markov Decision Process, and then solves the MDP (given an arbitrary reward signal) to generate advice. We evaluate our work in a simulated robot soccer environment and experimental results show improved agent performance when using the advice generated from the MDP for both a sub-task and the full soccer game.