NAPPO: Modular and scalable reinforcement learning in pytorch.
Albert BouGianni De FabritiisPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- reinforcement learning methods
- highly flexible
- modular structure
- highly scalable
- learning process
- artificial neural networks
- machine learning
- memory efficient
- web scale
- policy search
- relational reinforcement learning
- real time
- learning agents
- modular neural networks
- temporal difference
- model free
- optimal control
- transfer learning
- lightweight
- dynamic programming
- multi agent
- decision making
- data mining