Multi-Agent Reinforcement Learning for Energy Harvesting Two-Hop Communications With a Partially Observable System State.
Andrea OrtizTobias WeberAnja KleinPublished in: IEEE Trans. Green Commun. Netw. (2021)
Keyphrases
- partially observable
- multi agent reinforcement learning
- state space
- reinforcement learning
- decision problems
- markov decision processes
- partial observations
- belief state
- dynamical systems
- infinite horizon
- search space
- orders of magnitude
- decision making
- markov chain
- dynamic programming
- belief revision
- reward function
- learning process
- multi agent systems
- knowledge base