rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch.
Adam StookePieter AbbeelPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- source code
- transfer learning
- model free
- learning algorithm
- reinforcement learning algorithms
- machine learning
- fully functional
- state space
- optimal policy
- temporal difference
- robotic control
- real time
- multi agent reinforcement learning
- static analysis
- learning process
- decision trees
- information systems
- real world
- databases