Abstract | ||
---|---|---|
We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL apply to general multi-agent systems, and are expected to scale well to large systems.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.5555/3398761.3398997 | AAMAS '19: International Conference on Autonomous Agents and Multiagent Systems
Auckland
New Zealand
May, 2020 |
DocType | ISSN | ISBN |
Conference | Proceedings of the 19th International Conference on Autonomous
Agents and Multiagent Systems (AAMAS), 2020 | 978-1-4503-7518-4 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guohui Ding | 1 | 129 | 17.14 |
Koh Joewie J. | 2 | 0 | 0.34 |
Kelly Merckaert | 3 | 0 | 1.01 |
Bram Vanderborght | 4 | 1029 | 117.65 |
Nicotra, M. | 5 | 34 | 9.25 |
Christoffer R. Heckman | 6 | 12 | 10.78 |
Alessandro Roncone | 7 | 21 | 6.98 |
Lijun Chen | 8 | 657 | 52.72 |