Quantum reinforcement learning in continuous action space.
Shaojun WuShan JinDingding WenXiaoting WangPublished in: CoRR (2020)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- real valued
- continuous state
- continuous state spaces
- stochastic processes
- action selection
- control policies
- reinforcement learning methods
- continuous action
- state action
- markov decision problems
- function approximation
- function approximators
- reinforcement learning algorithms
- markov decision process
- single agent
- temporal difference
- non stationary
- multi agent systems
- search algorithm
- control problems
- supervised learning