Abstract | ||
---|---|---|
tic knowledge to aid decision-making has been studied Planners have traditionally not handled domain un- certainty, postponing that poesib'xlity to error moni- toring routines during the execution of the plan. In real-world domains with incomplete knowledge, this results in inevitable delays d'-e to rep)annlug. This pa- per describes a planner that considers the rellabflity of the agent's actions (leaxned from previous experience) while generating a plan. This is done by incorporat- ing into the domain representation, the probabilities that the effects of an action will be observed after its execution. These probabilities may depend on the cur- rent state of the environment, allowing the formation of hard and soft constraints for actions. Action selec- tion is performed by computing an ~expected utility = for each action by a bidirectional spreading activa- tion process which propagates goal utilities backwaxd and predicted states of the environment forwexd. This connectionist approach allows the simultaneous gener- ation of multiple plans, resulting in the availability of fall-back pIans if the one with the highest probability of succeeding fails. |
Year | Venue | Keywords |
---|---|---|
1994 | AIPS | expected utility |
Field | DocType | Citations |
Incomplete knowledge,State of the Environment,Expected utility hypothesis,Computer science,Planner,Artificial intelligence,Action selection,Connectionism | Conference | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sugato Bagchi | 1 | 311 | 41.10 |
Gautam Biswas | 2 | 1594 | 233.43 |
Kazuhiko Kawamura | 3 | 366 | 68.28 |