CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms.
Shengyi HuangRousslan Fernand Julien DossaChang YeJeff BragaPublished in: CoRR (2021)
Keyphrases
- reinforcement learning algorithms
- high quality
- reinforcement learning
- markov decision processes
- model free
- state space
- learning algorithm
- linear combination
- function approximation
- temporal difference
- machine learning
- reinforcement learning methods
- reinforcement learning problems
- higher order
- policy search
- multiagent reinforcement learning
- partially observable environments
- markov chain
- multi agent
- decision making