Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification.

Ben Eysenbach Sergey Levine Ruslan Salakhutdinov

Published in: NeurIPS (2021)

Keyphrases

policy search
reinforcement learning
supervised learning
machine learning
training set
support vector machine svm
training examples
markov decision processes
support vector
dynamic programming
support vector machine
machine learning algorithms
reward function
reinforcement learning algorithms
continuous state