d3rlpy: An Offline Deep Reinforcement Learning Library.
Takuma SenoMichita ImaiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- machine learning
- model free
- real time
- policy search
- optimal control
- artificial intelligence
- learning process
- optimal policy
- temporal difference learning
- deep learning
- control policy
- markov decision processes
- reinforcement learning methods
- cross platform
- direct policy search
- control problems
- learning capabilities
- transfer learning
- evolutionary algorithm
- multi agent
- bayesian networks
- decision trees
- data mining