Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

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.

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

Tweets