d3rlpy: An Offline Deep Reinforcement Learning Library.
Takuma SenoMichita ImaiPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- real time
- model free
- robotic control
- reinforcement learning methods
- optimal policy
- machine learning
- relational reinforcement learning
- learning algorithm
- control problems
- multi agent reinforcement learning
- deep learning
- evolutionary algorithm
- website
- function approximators
- temporal difference learning
- continuous state
- data sets
- transition model
- markov decision process
- social networks
- information systems
- multi agent