Model-Based Reinforcement Learning and Neural-Network-Based Policy Compression for Spacecraft Rendezvous on Resource-Constrained Embedded Systems.
Zhibin YangLinquan XingZonghua GuYingmin XiaoYong ZhouZhiqiu HuangLei XuePublished in: IEEE Trans. Ind. Informatics (2023)
Keyphrases
- embedded systems
- resource constrained
- model based reinforcement learning
- markov decision processes
- optimal policy
- markov decision problems
- low cost
- policy iteration
- reinforcement learning
- partially observable markov decision processes
- software systems
- finite state
- infinite horizon
- partially observable
- state space
- decision problems
- relational data
- relational domains
- concept learning
- real time
- power consumption
- learning algorithm
- databases