Beobench: a toolkit for unified access to building simulations for reinforcement learning.
Arduin FindeisFiodar KazhamiakaScott JeenSrinivasan KeshavPublished in: e-Energy (2022)
Keyphrases
- artificial neural networks
- learning process
- reinforcement learning
- neural network
- learning algorithm
- function approximation
- state space
- numerical simulations
- dynamic programming
- model free
- optimal policy
- reinforcement learning algorithms
- markov decision process
- unified model
- function approximators
- temporal difference
- access control
- information access
- database systems
- web services
- decision making
- machine learning