ChainerRL: A Deep Reinforcement Learning Library.
Yasuhiro FujitaToshiki KataokaPrabhat NagarajanTakahiro IshikawaPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- model free
- reinforcement learning algorithms
- temporal difference learning
- relational reinforcement learning
- state space
- markov decision processes
- learning process
- learning algorithm
- stochastic approximation
- policy search
- database
- genetic algorithm
- deep learning
- optimal control
- function approximators
- control policy
- robotic control
- control problems
- learning classifier systems
- optimal policy
- sufficient conditions
- least squares
- knowledge base
- e learning
- databases