Building Portable Options: Skill Transfer in Reinforcement Learning
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 895-899.
Abstract
The options framework provides methods for reinforcement learning agents to build new high-level skills. However, since options are usually learned in the same state space as the problem the agent is solving, they cannot be used in other tasks that are similar but have different state spaces. We introduce the notion of learning options in agent-space, the space generated by a feature set that is present and retains the same semantics across successive problem instances, rather than in problem-space. Agent-space options can be reused in later tasks that share the same agent-space but have different problem-spaces. We present experimental results demonstrating the use of agent-space options in building transferrable skills, and show that they perform best when used in conjunction with problem-space options.
@inproceedings{ijcai2007p144,
title = {Building Portable Options: Skill Transfer in Reinforcement Learning},
author = {Konidaris, George Dimitri and Barto, Andrew G.},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {895--899},
year = {2007},
url = {https://ijcai.org/proceedings/2007/144},
}
TY - CPAPER TI - Building Portable Options: Skill Transfer in Reinforcement Learning AU - Konidaris, George Dimitri AU - Barto, Andrew G. T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 895 EP - 899 UR - https://ijcai.org/proceedings/2007/144 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
