4035 search results - page 511 / 807 » Useless Actions Are Useful |
210
click to vote
AROBOTS
1999
15 years 7 months ago
1999
We use reinforcement learning (RL) to compute strategies for multiagent soccer teams. RL may pro t signi cantly from world models (WMs) estimating state transition probabilities an...
180
click to vote
FAC
1998
15 years 7 months ago
1998
In the process-algebraic veri cation of systems with three or more components put in parallel, alphabet axioms are considered to be very useful. These are rules that exploit the i...
195
click to vote
PRESENCE
2002
15 years 7 months ago
2002
"It / I" is a two-character theater play where the human character I (played by a real actor) is taunted and played with by an autonomous computer character It on a comp...
179
click to vote
TSMC
2002
15 years 7 months ago
2002
Abstract--We present the STack ARchitecture (STAR) automaton. It is a fixed structure, multiaction, reward-penalty learning automaton, characterized by a star-shaped state transiti...
191
click to vote
CORR
2010
Springer
15 years 7 months ago
2010
Springer
Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of B...