Discriminator Soft Actor Critic without Extrinsic Rewards.
Daichi NishioDaiki KuyoshiToi TsunedaSatoshi YamanePublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- markov decision processes
- policy iteration
- reinforcement learning algorithms
- temporal difference
- approximate dynamic programming
- optimal control
- policy gradient
- function approximation
- state space
- neuro fuzzy
- gradient method
- dynamic programming
- model free
- average reward
- learning algorithm
- optimal policy
- control policy
- reward function
- reinforcement learning methods
- learning problems
- action space
- infinite horizon