Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- high speed
- reward shaping
- state space
- function approximation
- action space
- machine learning
- state action
- knowledge base
- physical design
- consistency checking
- reinforcement learning algorithms
- high density
- markov decision processes
- temporal difference
- circuit design
- model free
- query answering
- analog vlsi
- optimal policy
- fitted q iteration