On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning.
Marc Aurel VischerRobert Tjarko LangeHenning SprekelerPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- learning algorithm
- temporal difference
- model free
- symbolic representation
- multi agent
- learning process
- temporal difference learning
- state space
- optimal policy
- function approximation
- markov decision processes
- machine learning
- autonomous learning
- utility function
- higher level
- least squares
- learning problems
- supervised learning
- reinforcement learning algorithms
- dynamic programming
- risk aversion
- database
- unsupervised feature learning