Fast Online Reinforcement Learning Control Using State-Space Dimensionality Reduction.
Tomonori SadamotoAranya ChakraborttyJun-ichi ImuraPublished in: IEEE Trans. Control. Netw. Syst. (2021)
Keyphrases
- state space
- reinforcement learning
- dimensionality reduction
- control problems
- reinforcement learning algorithms
- markov decision processes
- optimal policy
- optimal control
- robot control
- control strategies
- dynamic programming
- continuous state spaces
- adaptive control
- state variables
- action selection
- control policy
- online learning
- function approximation
- heuristic search
- real time
- state abstraction
- markov chain
- low dimensional
- feature extraction
- markov decision process
- action space
- model free
- control system
- learning algorithm
- control policies
- control strategy
- partially observable
- reward function
- particle filter
- principal component analysis
- high dimensional
- multi agent
- robotic systems
- stochastic domains
- robotic control
- structure preserving
- high dimensionality
- machine learning