CORL: Research-oriented Deep Offline Reinforcement Learning Library.
Denis TarasovAlexander NikulinDmitry AkimovVladislav KurenkovSergey KolesnikovPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- state space
- real time
- dynamic programming
- multi agent
- learning algorithm
- case study
- learning process
- temporal difference
- supervised learning
- optimal control
- markov decision processes
- database
- data sets
- direct policy search
- robotic control
- early vision
- learning capabilities
- dynamical systems
- search engine
- artificial neural networks
- multi agent systems
- search algorithm
- information systems