Mask-based Latent Reconstruction for Reinforcement Learning.
Tao YuZhizheng ZhangCuiling LanYan LuZhibo ChenPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- function approximation
- three dimensional
- image reconstruction
- learning algorithm
- multi agent
- high resolution
- state space
- compressed sensing
- latent variables
- reinforcement learning algorithms
- dynamic programming
- reinforcement learning methods
- optimal policy
- tomographic reconstruction
- discrete tomography
- reconstruction process
- markov decision processes
- robotic control
- reconstruction method
- reconstructed image
- optimal control
- information retrieval
- shape recovery
- neural network
- transfer learning
- bit rate
- x ray
- policy search