Safe Reinforcement Learning in Continuous State Spaces.
Takumi UmemotoTohgoroh MatsuiAtsuko MutohKoichi MoriyamaNobuhiro InuzukaPublished in: GCCE (2019)
Keyphrases
- continuous state spaces
- reinforcement learning
- state space
- continuous state
- control problems
- markov decision processes
- action space
- function approximation
- rl algorithms
- partially observable markov decision processes
- heuristic search
- robot navigation
- model free
- temporal difference
- markov decision process
- machine learning
- reinforcement learning algorithms
- partially observable
- neural network
- markov chain
- learning algorithm