GLDQN: Explicitly Parameterized Quantile Reinforcement Learning for Waste Reduction.
Sami JullienMozhdeh AriannezhadPaul GrothMaarten de RijkePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- state space
- optimal policy
- databases
- environmental impact
- reduction method
- model free
- markov decision processes
- transfer learning
- supervised learning
- website
- artificial intelligence
- active learning
- evolutionary algorithm
- learning process
- multi agent
- decision trees
- search engine
- control problems
- genetic algorithm
- robot control
- multi agent reinforcement learning
- data sets
- direct policy search