Generating Plans To Succeed in Uncertain Environments

tic knowledge to aid decision-making has been studied Planners have traditionally not handled domain uncertainty, postponing that poesib’xlity to error monitoring 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 paper describes a planner that considers the rellabflity of the agent’s actions (leaxned from previous experience) while generating a plan. This is done by incorporating into the domain representation, the probabilities that the effects of an action will be observed after its execution. These probabilities may depend on the current state of the environment, allowing the formation of hard and soft constraints for actions. Action selection is performed by computing an ~expected utility = for each action by a bidirectional spreading activation process which propagates goal utilities backwaxd and predicted states of the environment forwexd. This connectionist approach allows the simultaneous generation of multiple plans, resulting in the availability of fall-back pIans if the one with the highest probability of succeeding fails.