Improving Policies via Search in Cooperative Partially Observable Games.
Adam LererHengyuan HuJakob N. FoersterNoam BrownPublished in: AAAI (2020)
Keyphrases
- partially observable
- cooperative
- markov decision problems
- optimal policy
- state space
- decision problems
- search algorithm
- partial observability
- infinite horizon
- markov decision processes
- game theory
- search space
- reward function
- reinforcement learning
- partial observations
- search strategies
- partially observable markov decision processes
- multi agent systems
- partially observable environments
- markov decision process
- partially observable domains
- belief state
- search methods
- constraint programming
- probability distribution
- evolutionary algorithm