Diverse Projection Ensembles for Distributional Reinforcement Learning.
Moritz Akiya ZangerWendelin BoehmerMatthijs T. J. SpaanPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- ensemble learning
- decision trees
- robotic control
- policy search
- reinforcement learning algorithms
- temporal difference
- model free
- markov decision processes
- co occurrence
- wide variety
- optimal control
- radon transform
- projection method
- learning process
- image sequences
- projector camera
- multi agent
- multi agent reinforcement learning
- stochastic approximation
- classifier ensemble
- multi agent systems
- prediction accuracy
- convex sets
- random forests
- supervised learning
- ensemble methods