SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation.
Haruka KiyoharaRen KishimotoKosuke KawakamiKen KobayashiKazuhide NakataYuta SaitoPublished in: CoRR (2023)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- model free
- policy iteration
- markov decision processes
- function approximation
- least squares
- td learning
- monte carlo
- reinforcement learning algorithms
- state space
- rl algorithms
- temporal difference learning
- variance reduction
- optimal policy
- action space
- semi parametric
- evaluation function
- learning problems
- machine learning
- dynamic programming
- action selection
- optimal control
- reinforcement learning methods
- supervised learning
- learning process
- partially observable markov decision processes
- multi agent
- markov chain