RL: Generic reinforcement learning codebase in TensorFlow.
Bryan M. LiAlexander Imani Cowen-RiversPiotr KozakowskiDavid TaoSiddhartha KamalakaraNitarshan RajkumarHariharan SezhiyanSicong HuangAidan N. GomezPublished in: J. Open Source Softw. (2019)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- temporal difference
- state space
- rl algorithms
- machine learning
- markov decision processes
- control problems
- domain specific
- transfer learning
- learning algorithm
- optimal policy
- learning process
- dynamic programming
- action space
- multi agent
- reinforcement learning methods
- learning problems
- exploration strategy
- learning classifier systems
- supervised learning
- action selection
- actor critic
- approximate dynamic programming
- direct policy search
- continuous state
- partially observable
- learned knowledge
- learning agents
- state action
- function approximators
- policy iteration
- policy gradient
- active learning
- policy search
- optimal control
- state and action spaces
- learning tasks