Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback.
Jangwon KimHangyeol KimJiwook KangJongchan BaekSoohee HanPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- delayed feedback
- learning algorithm
- dynamic environments
- computationally efficient
- function approximation
- machine learning
- multi agent
- robotic control
- multi agent environments
- model free
- neural network
- markov decision process
- markov decision processes
- dynamic programming
- database
- monte carlo
- multi agent reinforcement learning
- policy search
- optimal policy