|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00)
Function approximation based multi-agent reinforcement learning
Vancouver, British Columbia, Canada
November 13-November 15
ISBN: 0-7695-0909-6
| ASCII Text | x | ||
| O. Abul, F. Polat, R. Alhajj, "Function approximation based multi-agent reinforcement learning," 2012 IEEE 24th International Conference on Tools with Artificial Intelligence, pp. 0036, 12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00), 2000. | |||
| BibTex | x | ||
| @article{ 10.1109/TAI.2000.889843, author = {O. Abul and F. Polat and R. Alhajj}, title = {Function approximation based multi-agent reinforcement learning}, journal ={2012 IEEE 24th International Conference on Tools with Artificial Intelligence}, volume = {0}, year = {2000}, isbn = {0-7695-0909-6}, pages = {0036}, doi = {http://doi.ieeecomputersociety.org/10.1109/TAI.2000.889843}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - 2012 IEEE 24th International Conference on Tools with Artificial Intelligence TI - Function approximation based multi-agent reinforcement learning SN - 0-7695-0909-6 SP EP A1 - O. Abul, A1 - F. Polat, A1 - R. Alhajj, PY - 2000 KW - learning (artificial intelligence); multi-agent systems; function approximation; function approximation; multi-agent reinforcement learning; multi-agent based domain independent coordination mechanisms; coordination information; state transitions; reward distribution; region-wide joint rewards; Adversarial Food-Collecting World; multi-agent environments VL - 0 JA - 2012 IEEE 24th International Conference on Tools with Artificial Intelligence ER - | |||
Abstract: The paper presents two new multi-agent based domain independent coordination mechanisms for reinforcement learning. The first mechanism allows agents to learn coordination information from state transitions and the second one from the observed reward distribution. In this way, the latter mechanism tends to increase region-wide joint rewards. The selected experimented domain is Adversarial Food-Collecting World (AFCW), which can be configured both as single and multi-agent environments. Experimental results show the effectiveness of these mechanisms.
Index Terms:
learning (artificial intelligence); multi-agent systems; function approximation; function approximation; multi-agent reinforcement learning; multi-agent based domain independent coordination mechanisms; coordination information; state transitions; reward distribution; region-wide joint rewards; Adversarial Food-Collecting World; multi-agent environments
Citation:
O. Abul, F. Polat, R. Alhajj, "Function approximation based multi-agent reinforcement learning," ictai, pp.0036, 12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00), 2000
Usage of this product signifies your acceptance of the Terms of Use.