Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets.
Anirudhan BadrinathYannis Flet-BerliacAllen NieEmma BrunskillPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- supervised learning
- function approximation
- unsupervised learning
- learning algorithm
- kernel based learning
- state space
- machine learning
- fuzzy logic
- reinforcement learning algorithms
- temporal difference
- model free
- fault diagnosis
- training examples
- active learning
- semi supervised learning
- multi agent
- learning problems
- multiple instance learning
- statistical learning
- learning tasks
- training data
- learning process
- markov decision processes
- robotic control
- power transformers
- supervised machine learning
- target recognition
- autonomous vehicles
- training set
- learning classifier systems
- target tracking
- unlabeled data
- optimal control
- dynamic programming
- supervised classification
- expert systems
- training samples
- multi target
- temporal difference learning
- reinforcement learning methods
- power system
- policy search
- data sets
- transfer learning
- incipient fault