A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits.
Ramin M. HasaniMathias LechnerAlexander AminiDaniela RusRadu GrosuPublished in: ICML (2020)
Keyphrases
- reinforcement learning
- fitted q iteration
- network architecture
- neural network
- lateral inhibition
- real world
- function approximation
- optimal policy
- learning algorithm
- high speed
- state space
- learning problems
- bio inspired
- model free
- neural model
- markov decision processes
- dynamic programming
- optimal control
- control system
- learning rules
- sensory inputs
- delay insensitive
- robotic control
- learning process
- supervised learning