Decentralized fused-learner architectures for Bayesian reinforcement learning.
Augustin-Alexandru SaucanSubhro DasMoe Z. WinPublished in: Artif. Intell. (2024)
Keyphrases
- bayesian reinforcement learning
- optimal policy
- monte carlo tree search
- reinforcement learning
- learning process
- e learning
- learning environment
- peer to peer
- monte carlo
- multi agent
- markov decision processes
- dynamic programming
- objective function
- decision makers
- infinite horizon
- partially observable markov decision processes