Deep Reinforcement Learning and its Neuroscientific Implications.
Matthew BotvinickJane X. WangWill DabneyKevin J. MillerZeb Kurth-NelsonPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- reinforcement learning algorithms
- markov decision processes
- temporal difference
- dynamic programming
- deep learning
- optimal policy
- action space
- learning process
- temporal difference learning
- stochastic approximation
- multi agent reinforcement learning
- database
- robotic control
- medical images
- evolutionary algorithm
- objective function
- decision trees
- information retrieval