Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research.
Johan Samir Obando-CeronPablo Samuel CastroPublished in: ICML (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- learning process
- markov decision processes
- optimal policy
- machine learning
- model free
- dynamic programming
- policy search
- decision trees
- optimal control
- learning classifier systems
- multi agent reinforcement learning
- control problems
- robotic control
- active learning
- evolutionary learning
- stochastic approximation
- temporal difference learning
- action space
- deep learning
- database
- reward function
- action selection
- learning algorithm
- case study
- multiscale
- supervised learning
- least squares
- multi agent systems