Robust Reinforcement Learning on State Observations with Learned Optimal Adversary.
Huan ZhangHongge ChenDuane S. BoningCho-Jui HsiehPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- state space
- dynamic programming
- optimal control
- control policy
- optimal policy
- multi agent
- hidden state
- learning process
- optimal solution
- markov decision processes
- machine learning
- state variables
- temporal difference
- reinforcement learning algorithms
- action space
- state dependent
- initially unknown