Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions.
Ezgi KorkmazJonah Brown-CohenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- decision making
- learning algorithm
- dynamic programming
- state space
- real world
- robust estimation
- partial occlusion
- decision makers
- multiscale
- information systems
- least squares
- computationally efficient
- markov decision processes
- automatic detection
- data mining
- decision process
- parameter tuning
- database
- model free
- reinforcement learning methods
- multi agent reinforcement learning