Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-Agent Urban Driving Environment.
Aizaz SharifDusica MarijanPublished in: QRS (2022)
Keyphrases
- reinforcement learning
- multi agent
- multi agent environments
- optimal policy
- reinforcement learning agents
- cooperative
- state space
- robotic systems
- agent behavior
- multi agent systems
- dynamic environments
- autonomous agents
- robocup soccer
- control policies
- policy search
- reward function
- semi autonomous
- autonomous systems
- exploration strategy
- function approximation
- multiagent reinforcement learning
- autonomous learning
- markov decision process
- learning agents
- tabula rasa
- real time
- partially observable markov decision processes
- single agent
- markov decision processes
- multiple agents
- reinforcement learning algorithms
- machine learning
- autonomous mental development
- dynamic programming
- mobile robot
- resolve conflicts
- decision problems
- urban areas
- multiple autonomous
- function approximators
- decentralized control
- multi agent reinforcement learning
- real robot
- service robots
- decision processes
- control policy