Single-Agent Policy Tree Search With Guarantees.
Laurent OrseauLevi H. S. LelisTor LattimoreThéophane WeberPublished in: CoRR (2018)
Keyphrases
- tree search
- single agent
- path finding
- larger problems
- policy gradient
- multi agent
- action space
- multiple agents
- search algorithm
- optimal policy
- heuristic search
- constraint propagation
- iterative deepening
- decision problems
- multi agent systems
- dynamic environments
- branch and bound
- path planning
- state space
- partially observable markov decision processes
- reinforcement learning
- rule learning
- hill climbing
- mathematical programming
- search tree
- initial state
- optimal path
- search space
- complexity analysis
- branch and bound algorithm
- special case
- learning algorithm