PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice.
Joseph SuarezPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- multi agent environments
- real world
- model free
- state space
- multi agent
- game playing
- highly dynamic
- markov decision processes
- reinforcement learning algorithms
- temporal difference learning
- learning algorithm
- optimal policy
- computing environments
- machine learning
- robotic control
- markov decision process
- real time
- autonomous robots
- optimal control
- dynamic programming
- evolutionary algorithm
- artificial neural networks
- database systems
- decision trees
- multimedia
- databases