A Gentle Lecture Note on Filtrations in Reinforcement Learning.
Wouter J. A. van HeeswijkPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- control problems
- reinforcement learning algorithms
- model free
- temporal difference
- optimal policy
- decision making
- multimedia
- function approximators
- dynamic programming
- state space
- multi agent reinforcement learning
- lecture videos
- direct policy search
- computer engineering
- robotic control
- real world
- partially observable
- markov decision processes
- supervised learning
- multi agent
- case study
- learning algorithm