Learning to Fly - a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control.
Jacopo PaneratiHehui ZhengSiqi ZhouJames XuAmanda ProrokAngela P. SchoelligPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- multi agent environments
- learning agents
- learning algorithm
- learning process
- control problems
- adaptive control
- learning capabilities
- supervised learning
- artificial intelligence
- state space
- action selection
- learning tasks
- reinforcement learning algorithms
- robot control
- stochastic games
- learning systems
- learning problems
- autonomous learning
- autonomous agents
- machine learning
- temporal difference learning
- multi agent based simulation
- robot behavior
- multiagent environments
- neural network
- temporal difference
- autonomous robots
- learning community
- optimal control
- markov decision processes
- optimal policy
- dynamic programming
- computer science
- cooperative