451 search results - page 3 / 91 » Temporal Rewards for Performance Evaluation |
160
Voted
JAIR
2006
15 years 3 months ago
2006
A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decisiontheoretic...
158
Voted
VALUETOOLS
2006
ACM
15 years 9 months ago
2006
ACM
High-level stochastic description methods such as stochastic Petri nets, stochastic UML statecharts etc., together with specifications of performance variables (PVs), enable a co...
127
click to vote
AAAI
2006
15 years 5 months ago
2006
Coordinating multiple agents that need to perform a sequence of actions to maximize a system level reward requires solving two distinct credit assignment problems. First, credit m...
138
Voted
CHI
2010
ACM
15 years 10 months ago
2010
ACM
Contemporary lifestyle has become increasingly sedentary: little physical (sports, exercises) and much sedentary (TV, computers) activity. The nature of sedentary activity is self...
156
Voted
AAAI
2006
15 years 5 months ago
2006
As robots become a mass consumer product, they will need to learn new skills by interacting with typical human users. Past approaches have adapted reinforcement learning (RL) to a...