Implicit Offline Reinforcement Learning via Supervised Learning.
Alexandre PichéRafael PardinasDavid VázquezIgor MordatchChris PalPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- supervised learning
- learning algorithm
- kernel based learning
- function approximation
- state space
- temporal difference
- unsupervised learning
- learning tasks
- model free
- learning problems
- class labels
- markov decision processes
- learning process
- active learning
- machine learning
- semi supervised learning
- training examples
- reinforcement learning algorithms
- least squares
- supervised classification
- multi agent reinforcement learning
- real time
- labeled data
- multiple instance learning
- semi supervised
- training set
- information systems
- learning agent
- learning agents
- temporal difference learning
- policy search
- data sets