Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents.
Xian Yeow LeeYasaman EsfandiariKai Liang TanSoumik SarkarPublished in: CoRR (2020)
Keyphrases
- reinforcement learning agents
- action space
- reinforcement learning
- state space
- state abstraction
- dynamic environments
- multi agent
- markov decision processes
- single agent
- markov decision process
- optimal policy
- multi agent environments
- machine learning
- cooperative
- path planning
- stochastic processes
- function approximators
- learning algorithm