CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning.
Jinxin LiuLipeng ZuLi HeDonglin WangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- state space
- latent variables
- policy search
- learning algorithm
- computer vision
- three dimensional
- model free
- multi view
- markov decision processes
- action space
- reinforcement learning algorithms
- action selection
- real time
- optimal policy
- dynamic programming
- learning process
- multi agent
- transfer learning
- supervised learning
- probabilistic model
- latent variable models
- uncalibrated cameras
- learning agents
- temporal difference learning
- reinforcement learning methods
- policy gradient
- multi agent reinforcement learning
- machine learning