312 search results - page 32 / 63 » Learning Partially Observable Deterministic Action Models |
AI
1999
Springer
13 years 7 months ago
1999
Springer
In this paper, we first discuss the meaning of physical embodiment and the complexity of the environment in the context of multi-agent learning. We then propose a vision-based rei...
AI
1998
Springer
13 years 12 months ago
1998
Springer
This paper presents and evaluates sequential instance-based learning (SIBL), an approach to action selection based upon data gleaned from prior problem solving experiences. SIBL le...
ATAL
2007
Springer
13 years 11 months ago
2007
Springer
This paper extends the framework of dynamic influence diagrams (DIDs) to the multi-agent setting. DIDs are computational representations of the Partially Observable Markov Decisio...
ICRA
2006
IEEE
14 years 1 months ago
2006
IEEE
— Many application tasks require the cooperation of two or more robots. Humans are good at cooperation in shared workspaces, because they anticipate and adapt to the intentions a...
COLT
2006
Springer
13 years 11 months ago
2006
Springer
We consider online learning in repeated decision problems, within the framework of a repeated game against an arbitrary opponent. For repeated matrix games, well known results esta...