45 search results - page 5 / 9 » High-level reinforcement learning in strategy games |
ICML
2005
IEEE
16 years 15 days ago
2005
IEEE
Learning algorithms often obtain relatively low average payoffs in repeated general-sum games between other learning agents due to a focus on myopic best-response and one-shot Nas...
ATAL
2004
Springer
15 years 5 months ago
2004
Springer
This paper investigates a relatively new direction in Multiagent Reinforcement Learning. Most multiagent learning techniques focus on Nash equilibria as elements of both the learn...
107
click to vote
FLAIRS
2008
15 years 2 months ago
2008
Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typic...
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...
ECML
2004
Springer
15 years 5 months ago
2004
Springer
In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...