Overview of t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making.
William YueBo LiuPeter StonePublished in: AAMAS (2024)
Keyphrases
- decision making
- learning algorithm
- high accuracy
- data mining
- objective function
- dynamic programming
- learning scheme
- unsupervised learning
- learning process
- prior knowledge
- reinforcement learning
- noise tolerant
- learning mechanism
- detection method
- clustering method
- gaussian process latent variable models
- online learning
- feature set
- supervised learning
- support vector machine
- cost function
- image sequences