Boosting Soft Q-Learning by Bounding.
Jacob AdamczykVolodymyr MakarenkoStas TiomkinRahul V. KulkarniPublished in: CoRR (2024)
Keyphrases
- learning algorithm
- reinforcement learning
- function approximation
- cooperative
- upper bound
- state space
- multi agent
- stochastic approximation
- optimal policy
- multi agent reinforcement learning
- reinforcement learning algorithms
- feature selection
- potential field
- boosting algorithms
- base classifiers
- adaboost algorithm
- model free
- learning rate
- ensemble learning
- machine learning
- ensemble methods
- loss function
- noise tolerant
- temporal difference learning
- training set
- lower bound
- support vector
- boosting framework
- bucket brigade