A Generalist Reinforcement Learning Agent for Compressing Convolutional Neural Networks.
Gabriel Gonzalez-SahagunSantiago Enrique Conant-PablosJosé Carlos Ortiz-BaylissJorge M. Cruz-DuartePublished in: IEEE Access (2024)
Keyphrases
- learning agent
- convolutional neural networks
- reinforcement learning
- state space
- convolutional network
- learning capabilities
- learning algorithm
- reinforcement learning algorithms
- function approximation
- selective perception
- solving problems
- model free
- learning tasks
- dynamic programming
- multi agent
- reward function
- machine learning
- learning process
- single agent
- multi agent systems
- data mining
- markov decision processes
- optimal policy
- random walk
- search algorithm