Yao Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yao Ma has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kohei Hatano
Kyushu University
1 shared publication - Masashi Sugiyama
RIKEN Center for Advanced Intelligence Project
1 shared publication - Tingting Zhao
Tianjin University of Science and Technology
1 shared publication
Latest Publications
- 1 March 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (3) , 563-593
An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
We consider the learning problem under an online Markov decision process (MDP) aimed at learning the time-dependent decision-making policy of an agent that minimizes the regret—the difference from the best fixed policy. The difficulty of online MDP learning is that the reward function changes over time. In this letter, we show that a simple online policy gradient algorithm achieves regret for T steps under a certain concavity assumption and under a strong concavity assumption. To the best of our knowledge, this is the first work to present an online MDP algorithm that can handle continuous state, action, and parameter spaces with guarantee. We also illustrate the behavior of the proposed online policy gradient method through experiments.
- 1 March 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (3) , 563-593
An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
We consider the learning problem under an online Markov decision process (MDP) aimed at learning the time-dependent decision-making policy of an agent that minimizes the regret—the difference from the best fixed policy. The difficulty of online MDP learning is that the reward function changes over time. In this letter, we show that a simple online policy gradient algorithm achieves regret for T steps under a certain concavity assumption and under a strong concavity assumption. To the best of our knowledge, this is the first work to present an online MDP algorithm that can handle continuous state, action, and parameter spaces with guarantee. We also illustrate the behavior of the proposed online policy gradient method through experiments.