Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Risk-sensitive Actor-free Policy via Convex Optimization (2307.00141v1)

Published 30 Jun 2023 in cs.LG

Abstract: Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensitive criterion based on the conditional value at risk. The risk-sensitive objective function is modeled using an input-convex neural network ensuring convexity with respect to the actions and enabling the identification of globally optimal actions through simple gradient-following methods. Experimental results demonstrate the efficacy of our approach in maintaining effective risk control.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (11)
  1. Input convex neural networks. In International Conference on Machine Learning, pages 146–155. PMLR, 2017.
  2. Coherent measures of risk. Mathematical finance, 9(3):203–228, 1999.
  3. Addressing function approximation error in actor-critic methods. In International conference on machine learning, pages 1587–1596. PMLR, 2018.
  4. A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 16(1):1437–1480, 2015.
  5. Learning to walk in the real world with minimal human effort. In Conference on Robot Learning, pages 1110–1120. PMLR, 2021.
  6. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR, 2015.
  7. Volodymyr Mnih et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, 2015.
  8. Optimizing the CVaR via sampling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 29, pages 2993–2999, 2015.
  9. Worst cases policy gradients. In Conference on Robot Learning, pages 1078–1093. PMLR, 2020.
  10. Numerical optimization. Springer Science, 35(67-68):7, 1999.
  11. WCSAC: Worst-case soft actor critic for safety-constrained reinforcement learning, 2021.
Citations (1)

Summary

We haven't generated a summary for this paper yet.