Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control.
Tsui-Wei WengKrishnamurthy (Dj) DvijothamJonathan UesatoKai XiaoSven GowalRobert StanforthPushmeet KohliPublished in: ICLR (2020)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control system
- robot control
- state space
- control strategy
- function approximation
- neural network
- control method
- adaptive control
- action space
- database
- action selection
- markov decision processes
- reinforcement learning algorithms
- continuous domains
- multi agent
- machine learning
- data sets