On Computing Universal Plans for Partially Observable Multi-Agent Path Finding.

Fengming Zhu Fangzhen Lin

Published in: CoRR (2023)

Keyphrases

partially observable
path finding
multi agent
reinforcement learning
single agent
state space
action models
planning domains
heuristic search

decision problems
markov decision processes
belief space
partial observability
dynamical systems
infinite horizon
planning under uncertainty
planning problems
partial observations

path planning
partially observable markov decision processes
classical planning
belief state
rule learning
search algorithm
ai planning
optimal policy

machine learning
hill climbing
reward function
plan generation
genetic algorithm
search strategies
model checking
control system