Collaborative Partially-Observable Reinforcement Learning Using Wireless Communications.
Eisaku KoKwang-Cheng ChenShao-Yu LienPublished in: ICC (2021)
Keyphrases
- partially observable
- wireless communication
- reinforcement learning
- state space
- wireless networks
- markov decision processes
- partial observability
- decision problems
- short range
- partially observable domains
- computer simulation
- wireless sensor networks
- dynamical systems
- communication networks
- partially observable environments
- partial observations
- hidden state
- function approximation
- markov decision problems
- model free
- infinite horizon
- reward function
- reinforcement learning algorithms
- action models
- belief state
- optimal policy
- fourth generation
- multi agent
- temporal difference
- cognitive radio
- transfer learning
- heuristic search
- partially observable markov decision process
- sufficient conditions
- dynamic programming