Halit Bener Suay
ABSTRACT
Many different robot learning from demonstration methods have been applied and tested in various environments recently. Representation of learned plans, tasks and policies often depends on the technique due to method-specific parameters. An agent that is able to switch between representations can apply its knowledge to different algorithms. This flexibility can be useful for a human teacher when training the agent. In this work we present a process to convert learned policies with two specific methods, Confidence-Based Autonomy (CBA) and Interactive Reinforcement Learning (Int-RL), to each other. Our finding suggests that it is possible for an agent to learn a policy with either CBA or Int-RL method and execute the task with the other with the benefit of previously learned knowledge.
- B. D. Argall, S. Chernova, M. Veloso, and B. Browning. A survey of robot learning from demonstration. Robot. Auton. Syst., 57:469--483, May 2009. Google Scholar
Digital Library
- S. Chernova and M. Veloso. Interactive policy learning through confidence-based autonomy. J. Artificial Intelligence Research, pages 1--25, 2009. Google ScholarDigital Library
- A. L. Thomaz and C. Breazeal. Adding guidance to interactive reinforcement learning. In Proceedings of the Twentieth Conference on Artificial Intelligence (AAAI), 2006.Google Scholar
Index Terms
- Policy transformation for learning from demonstration
Recommendations
Inverse Reinforcement Learning from Failure
AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent SystemsInverse reinforcement learning (IRL) allows autonomous agents to learn to solve complex tasks from successful demonstrations. However, in many settings, e.g., when a human learns the task by trial and error, failed demonstrations are also readily ...
Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain
Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are ...
Active deep Q-learning with demonstration
AbstractReinforcement learning (RL) is a machine learning technique aiming to learn how to take actions in an environment to maximize some kind of reward. Recent research has shown that although the learning efficiency of RL can be improved with expert ...
Comments