Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Code to reproduce the experiments illustrated in our paper.

Our experiments are split into either tabular experiments, or experiments in an option trading domain. The code for each set of experiments can be found in the tabular and option_trading directories respectively.

Citing

If you find our work useful, please consider referencing us in your paper:

Tyler Kastner, Murat A. Erdogdu, and Amir-massoud Farahmand. Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning Learning. In Advances in Neural Information Processing Systems, 2023.

@inproceedings{kastner2023distributional,
  title={Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning},
  author={Tyler Kastner and Murat A Erdogdu and Amir-massoud Farahmand},
  booktitle={Thirty-Seventh Conference on Neural Information Processing Systems},
  year={2023}
}