Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 152 tok/s
Gemini 2.5 Pro 48 tok/s Pro
GPT-5 Medium 27 tok/s Pro
GPT-5 High 32 tok/s Pro
GPT-4o 87 tok/s Pro
Kimi K2 204 tok/s Pro
GPT OSS 120B 429 tok/s Pro
Claude Sonnet 4.5 35 tok/s Pro
2000 character limit reached

A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays (2312.15091v2)

Published 22 Dec 2023 in cs.LG and math.OC

Abstract: In this paper, we study asynchronous stochastic approximation algorithms without communication delays. Our main contribution is a stability proof for these algorithms that extends a method of Borkar and Meyn by accommodating more general noise conditions. We also derive convergence results from this stability result and discuss their application in important average-reward reinforcement learning problems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. V. S. Borkar. Asynchronous stochastic approximations. SIAM J. Control Optim., 36(3):840–851, 1998.
  2. V. S. Borkar. Erratum: Asynchronous stochastic approximations. SIAM J. Control Optim., 38(2):662–663, 2000.
  3. V. S. Borkar and S. Meyn. The o.d.e. method for convergence of stochastic approximation and reinforcement learning. SIAM J. Control Optim., 38(2):447–469, 2000.
  4. V. S. Borkar. Stochastic Approximations: A Dynamical Systems Viewpoint. Springer, New York, 2009.
  5. Stochastic Approximation and Recursive Algorithms and Applications. Springer, New York, 2nd edition, 2003.
  6. Learning algorithms for Markov decision processes with average cost. SIAM Journal on Control and Optimization, 40(3):681–698, 2001.
  7. Learning and planning in average-reward Markov decision processes. In Proc. Int. Conf. Machine Learning (ICML), pages 10653–10662, 2021.
  8. Average-reward learning and planning with options. In Proc. Advances in Neural Information Processing Systems (NeurIPS), pages 22758–22769, 2021.
  9. On convergence of average-reward off-policy algorithms in weakly communicating MDPs. arXiv Preprint, forthcoming (2024).
  10. J. Tsitsiklis. Asynchronous stochastic approximation and Q-learning. Mach. Learning, 16:195–202, 1994.
  11. H. Yu and D. P. Bertsekas. On boundedness of Q-learning iterates for stochastic shortest path problems. Math. Oper. Res., 38:209–227, 2013.
  12. R. M. Dudley. Real Analysis and Probability. Cambridge University Press, Cambridge, 2002.
  13. J. Doob. Stochastic Processes. Wiley and Sons, New York, 1953.
  14. J. Neveu. Discrete Parameter Martingales. North-Holland, Amsterdam, 1975.
  15. S. Bhatnagar. The Borkar–Meyn theorem for asynchronous stochastic approximations. Systems Control Lett., 60:472–478, 2011.

Summary

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

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 tweet and received 0 likes.

Upgrade to Pro to view all of the tweets about this paper: