Fast Real-Time Reinforcement Learning for Partially-Observable Large-Scale Systems.
Tomonori SadamotoAranya ChakraborttyPublished in: IEEE Trans. Artif. Intell. (2020)
Keyphrases
- partially observable
- reinforcement learning
- real time
- partial observability
- state space
- markov decision processes
- partially observable domains
- decision problems
- dynamical systems
- hidden state
- complex systems
- function approximation
- reward function
- belief space
- partially observable environments
- linear programming
- search algorithm
- learning algorithm