Tata Institute of Fundamental Research
Decentralized Control of Markov Teams and Games with Partial Information
STCS Seminar
Speaker:
Eitan Altman (The National Institute for Research in
Computer Science and Automation (INRIA)
France)
Organiser:
Sandeep K Juneja
Date:
Thursday, 20 Dec 2018, 11:30 to 12:30
Venue:
A-201 (STCS Seminar Room)
(Scan to add to calendar)
Abstract:
Abstract: We consider in this talk distributed control by agents that have a common clock. The information available to agents at time t may vary from one agent to another. We show how to transform such problems into equivalent Markov Decision Processes with full information.
We study in particular the 1 step delay sharing information structure for problems of constrained Markov teams as well as for stochastic games. Both cases present extra complexity due to the fact that optimal policies require randomization. We present applications to power control problems.
| Speaker: | Eitan Altman (The National Institute for Research in Computer Science and Automation (INRIA) France) |
| Organiser: | Sandeep K Juneja |
| Date: | Thursday, 20 Dec 2018, 11:30 to 12:30 |
| Venue: | A-201 (STCS Seminar Room) |
(Scan to add to calendar)
Abstract:
Abstract: We consider in this talk distributed control by agents that have a common clock. The information available to agents at time t may vary from one agent to another. We show how to transform such problems into equivalent Markov Decision Processes with full information.
We study in particular the 1 step delay sharing information structure for problems of constrained Markov teams as well as for stochastic games. Both cases present extra complexity due to the fact that optimal policies require randomization. We present applications to power control problems.
We study in particular the 1 step delay sharing information structure for problems of constrained Markov teams as well as for stochastic games. Both cases present extra complexity due to the fact that optimal policies require randomization. We present applications to power control problems.