Fingerprint Policy Optimisation for Robust Reinforcement Learning.
Supratik PaulMichael A. OsborneShimon WhitesonPublished in: ICML (2019)
Keyphrases
- reinforcement learning
- optimal policy
- genetic algorithm
- learning algorithm
- policy search
- markov decision process
- state and action spaces
- markov decision processes
- function approximation
- markov decision problems
- policy gradient methods
- machine learning
- policy evaluation
- control policy
- policy iteration
- expected cost
- image enhancement
- state space