Recomposing the Reinforcement Learning Building Blocks with Hypernetworks.
Elad SarafianShai KeynanSarit KrausPublished in: ICML (2021)
Keyphrases
- building blocks
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- temporal difference
- multi agent
- learning algorithm
- temporal difference learning
- machine learning
- reinforcement learning methods
- back end
- data sets
- robotic control
- model free
- database
- optimal control
- markov decision processes
- dynamic programming
- learning process
- real world
- databases
- transfer learning
- supervised learning
- real robot
- text databases
- case study
- autonomous learning
- multi agent reinforcement learning
- policy search