Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

• URL: http://arxiv.org/abs/2310.02671v2
• Date: Mon, 6 May 2024 16:29:41 GMT
• Title: Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
• Authors: Sara Klein, Simon Weissmann, Leif Döring,
• Abstract summary: Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In practice all parameters are often trained simultaneously, ignoring the inherent structure suggested by dynamic programming. This paper introduces a combination of dynamic programming and policy gradient called dynamic policy gradient, where the parameters are trained backwards in time.
• Score: 0.40964539027092917
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems, but also in the training of large language models. In contrast to infinite horizon MDPs optimal policies are not stationary, policies must be learned for every single epoch. In practice all parameters are often trained simultaneously, ignoring the inherent structure suggested by dynamic programming. This paper introduces a combination of dynamic programming and policy gradient called dynamic policy gradient, where the parameters are trained backwards in time. For the tabular softmax parametrisation we carry out the convergence analysis for simultaneous and dynamic policy gradient towards global optima, both in the exact and sampled gradient settings without regularisation. It turns out that the use of dynamic policy gradient training much better exploits the structure of finite- time problems which is reflected in improved convergence bounds.

Related papers

• Two-Stage ML-Guided Decision Rules for Sequential Decision Making under Uncertainty [55.06411438416805]
  Sequential Decision Making under Uncertainty (SDMU) is ubiquitous in many domains such as energy, finance, and supply chains. Some SDMU are naturally modeled as Multistage Problems (MSPs) but the resulting optimizations are notoriously challenging from a computational standpoint. This paper introduces a novel approach Two-Stage General Decision Rules (TS-GDR) to generalize the policy space beyond linear functions. The effectiveness of TS-GDR is demonstrated through an instantiation using Deep Recurrent Neural Networks named Two-Stage Deep Decision Rules (TS-LDR)
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Elementary Analysis of Policy Gradient Methods [3.468656086349638]
  This paper focuses on the discounted MDP setting and conduct a systematic study of the aforementioned policy optimization methods. Several novel results are presented, including 1) global linear convergence of projected policy gradient for any constant step size, 2) sublinear convergence of softmax policy gradient for any constant step size, 3) global linear convergence of softmax natural policy gradient for any constant step size, 4) global linear convergence of entropy regularized softmax policy gradient for a wider range of constant step sizes than existing result, 5) tight local linear convergence rate of entropy regularized natural policy gradient, and 6) a new and concise local quadratic convergence rate of soft
  arXiv  Detail & Related papers  (2024-04-04T11:16:16Z)
• Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process [11.01014302314467]
  We focus on optimizing deep neural networks parameterized differential equations (SDEs) We propose constraining the SDE to be consistent with its associated perturbation process. Our framework offers a versatile selection of policy gradient methods to effectively and efficiently train SDEs.
  arXiv  Detail & Related papers  (2024-03-07T02:24:45Z)
• Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs [107.28031292946774]
  We study the problem of computing an optimal policy of an infinite-horizon discounted Markov decision process (constrained MDP) We develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy. To the best of our knowledge, this work appears to be the first non-asymptotic policy last-iterate convergence result for single-time-scale algorithms in constrained MDPs.
  arXiv  Detail & Related papers  (2023-06-20T17:27:31Z)
• Policy Gradient for Rectangular Robust Markov Decision Processes [62.397882389472564]
  We introduce robust policy gradient (RPG), a policy-based method that efficiently solves rectangular robust Markov decision processes (MDPs) Our resulting RPG can be estimated from data with the same time complexity as its non-robust equivalent.
  arXiv  Detail & Related papers  (2023-01-31T12:40:50Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning [17.916366827429034]
  We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions. We propose an Anchor-changing Regularized Natural Policy Gradient framework, which can incorporate ideas from well-performing first-order methods.
  arXiv  Detail & Related papers  (2022-06-10T21:09:44Z)
• Softmax Policy Gradient Methods Can Take Exponential Time to Converge [60.98700344526674]
  The softmax policy gradient (PG) method is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. We demonstrate that softmax PG methods can take exponential time -- in terms of $mathcalS|$ and $frac11-gamma$ -- to converge.
  arXiv  Detail & Related papers  (2021-02-22T18:56:26Z)
• Entropy-Augmented Entropy-Regularized Reinforcement Learning and a Continuous Path from Policy Gradient to Q-Learning [5.185562073975834]
  entropy augmentation is reformulated and leads to a motivation to introduce an additional entropy term to the objective function. It results in a policy which monotonically improves while interpolating from the current policy to the softmax greedy policy.
  arXiv  Detail & Related papers  (2020-05-18T16:15:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.