Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies: Well-Posedness and Convergence (Extended Version)

2020-06-11

Abstract dynamic programming models are used to analyze $\lambda$-policy iteration with randomization algorithms. Particularly, contractive models with infinite policies are considered and it is shown that well-posedness of the $\lambda$-operator plays a central role in the algorithm. The operator is known to be well-posed for problems with finite states, but our analysis shows that it is also well-defined for the contractive models with infinite states studied. Similarly, the algorithm we analyze is known to converge for problems with finite policies, but we identify the conditions required to guarantee convergence with probability one when the policy space is infinite regardless of the number of states. Guided by the analysis, we exemplify a data-driven approximated implementation of the algorithm for estimation of optimal costs of constrained linear and nonlinear control problems. Numerical results indicate potentials of this method in practice.

📄 PDF Abstract BibTeX arXiv:1912.08504

Code (0)

등록된 구현이 없습니다.

Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies: Well-Posedness and Convergence

2020-06-08 · L4DC 2020 6 · Yuchao Li, Karl Henrik Johansson, Jonas Mårtensson

Safe and Efficient Off-Policy Reinforcement Learning

2016-06-08 · NeurIPS 2016 12 · Rémi Munos, Tom Stepleton, Anna Harutyunyan, Marc G. Bellemare

In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace($\lambda$), with three desire…

Atari Games reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Non-Asymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms

2025-02-20 · Zaiwei Chen, Sheng Zhang, Zhe Zhang, Shaan ul Haque 외

We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the non-asymptotic behavior of iterative algorithms in both deterministic and stochastic sett…

Q-Learning

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

2020-03-27 · Philip Amortila, Doina Precup, Prakash Panangaden, Marc G. Bellemare

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a var…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

On Convergence of Emphatic Temporal-Difference Learning

2015-06-08 · Huizhen Yu

We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) a…