Corpus ID: 219573757

Efficient Contextual Bandits with Continuous Actions

@article{Majzoubi2020EfficientCB,
  title={Efficient Contextual Bandits with Continuous Actions},
  author={Maryam Majzoubi and Chicheng Zhang and Rajan Chari and A. Krishnamurthy and J. Langford and Aleksandrs Slivkins},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.06040}
}
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments. 
4 Citations

Figures from this paper

References

SHOWING 1-10 OF 68 REFERENCES
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
A Contextual Bandit Bake-off
Efficient Optimal Learning for Contextual Bandits
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits
On Context-Dependent Clustering of Bandits
The Epoch-Greedy algorithm for contextual multi-armed bandits
Contextual Gaussian Process Bandit Optimization
Efficient Algorithms for Adversarial Contextual Learning
...
1
2
3
4
5
...