453 search results - page 2 / 91 » Learning from actions not taken: a multiagent learning algor... |
ICML
2003
IEEE
16 years 7 days ago
2003
IEEE
A satisfactory multiagent learning algorithm should, at a minimum, learn to play optimally against stationary opponents and converge to a Nash equilibrium in self-play. The algori...
ATAL
2009
Springer
15 years 6 months ago
2009
Springer
Creating coordinated multiagent policies in environments with uncertainty is a challenging problem, which can be greatly simplified if the coordination needs are known to be limi...
ATAL
2005
Springer
15 years 4 months ago
2005
Springer
2. THE MASM ALGORITHM An input to the MASM algorithm is a time-annotated multi-agent action sequence. The action sequence is then transformed into an action graph. An action graph ...
ICML
2002
IEEE
16 years 7 days ago
2002
IEEE
We present several new algorithms for multiagent reinforcement learning. A common feature of these algorithms is a parameterized, structured representation of a policy or value fu...
ECAI
2006
Springer
15 years 3 months ago
2006
Springer
We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive...