Flexibility of Emulation Learning from Pioneers in Nonstationary Environments
-
- SHINRIKI Moto
- Tokyo Denki University
-
- WAKABAYASHI Hiroaki
- Tokyo Denki University
-
- KONO Yu
- Tokyo Denki University
-
- TAKAHASHI Tatsuji
- Tokyo Denki University
Bibliographic Information
- Other Title
-
- 非定常環境における先駆者からのエミュレーション学習の柔軟性
Abstract
<p>In imitation learning, the agent observes specific action-state pair sequences of another agent (expert) and somehow reflect them into its own action. One of its implementations in reinforcement learning is the inverse reinforcement learning. We propose a new framework for social learning, emulation learning, which requires much less information from another agent (pioneer). In emulation learning, the agent is given only a certain level of achievement (accumulated rewards per episode). In this study, we implement emulation learning in the reinforcement learning setting by applying a model of satisficing action policy. We show that the emulation learning algorithm works well in a non-stationary reinforcement learning tasks, breaking the often observed trade-off like relationship between optimality and flexibility.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2019 (0), 2D3E402-2D3E402, 2019
The Japanese Society for Artificial Intelligence
- Tweet
Details
-
- CRID
- 1390282752372294272
-
- NII Article ID
- 130007658419
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed