Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies.
Aizaz SharifDusica MarijanPublished in: APSEC (2022)
Keyphrases
- multi agent
- reinforcement learning
- autonomous driving
- optimal policy
- reinforcement learning agents
- grand challenge
- multiagent reinforcement learning
- single agent
- policy search
- state space
- learning agents
- partially observable markov decision processes
- multi agent systems
- reward function
- stereo vision
- markov decision process
- cooperative
- control policy
- autonomous agents
- markov decision processes
- multi agent environments
- reinforcement learning algorithms
- multiagent systems
- dynamic environments
- learning algorithm
- high quality
- dynamic programming
- fitted q iteration