Reusing Trajectories in Policy Gradients Enables Fast Convergence

• URL: http://arxiv.org/abs/2506.06178v1
• Date: Fri, 06 Jun 2025 15:42:15 GMT
• Title: Reusing Trajectories in Policy Gradients Enables Fast Convergence
• Authors: Alessandro Montenegro, Federico Mansutti, Marco Mussi, Matteo Papini, Alberto Maria Metelli,
• Abstract summary: Policy gradient (PG) methods are a class of effective reinforcement learning algorithms.<n>We propose RPG (Retrospective Policy Gradient), a PG algorithm that combines old and new trajectories for policy updates.<n>Under established assumptions, RPG achieves a sample complexity of $widetildeO(epsilon-1)$, the best known rate in the literature.
• Score: 59.27926064817273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. These methods learn the parameters of parametric policies via stochastic gradient ascent, typically using on-policy trajectory data to estimate the policy gradient. However, such reliance on fresh data makes them sample-inefficient. Indeed, vanilla PG methods require $O(\epsilon^{-2})$ trajectories to reach an $\epsilon$-approximate stationary point. A common strategy to improve efficiency is to reuse off-policy information from past iterations, such as previous gradients or trajectories. While gradient reuse has received substantial theoretical attention, leading to improved rates of $O(\epsilon^{-3/2})$, the reuse of past trajectories remains largely unexplored from a theoretical perspective. In this work, we provide the first rigorous theoretical evidence that extensive reuse of past off-policy trajectories can significantly accelerate convergence in PG methods. We introduce a power mean correction to the multiple importance weighting estimator and propose RPG (Retrospective Policy Gradient), a PG algorithm that combines old and new trajectories for policy updates. Through a novel analysis, we show that, under established assumptions, RPG achieves a sample complexity of $\widetilde{O}(\epsilon^{-1})$, the best known rate in the literature. We further validate empirically our approach against PG methods with state-of-the-art rates.

Related papers

• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• 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)
• Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies [19.779044926914704]
  We develop improved global convergence guarantees for a general class of Fisher-non-degenerate parameterized policies. In this work, we propose a Normalized Policy Gradient method with Implicit Gradient Transport (N-PG-IGT) and derive a $tildemathcalO(varepsilon-2.5)$ sample complexity of this method. We further improve this complexity to $tilde mathcalmathcalO (varepsilon-2)$ by considering a Hessian-Aided Recursive Policy Gradient
  arXiv  Detail & Related papers  (2023-02-03T13:50:23Z)
• The Role of Baselines in Policy Gradient Optimization [83.42050606055822]
  We show that the emphstate value baseline allows on-policy. emphnatural policy gradient (NPG) to converge to a globally optimal. policy at an $O (1/t) rate gradient. We find that the primary effect of the value baseline is to textbfreduce the aggressiveness of the updates rather than their variance.
  arXiv  Detail & Related papers  (2023-01-16T06:28:00Z)
• Momentum-Based Policy Gradient with Second-Order Information [40.51117836892182]
  We propose a variance-reduced policy-gradient method, called SHARP, which incorporates second-order information into gradient descent. Unlike most previous work, our proposed algorithm does not require importance sampling which can compromise the advantage of variance reduction process. Our extensive experimental evaluations show the effectiveness of the proposed algorithm on various control tasks and its advantage over the state of the art in practice.
  arXiv  Detail & Related papers  (2022-05-17T11:56:50Z)
• On the Global Convergence of Momentum-based Policy Gradient [9.622367651590878]
  Policy gradient (PG) methods are popular and efficient for large-scale reinforcement learning. We study the global convergences of PG methods with momentum terms, which have been demonstrated to be efficient recipes for improving PG methods. Our work is the first one that obtains global convergence results for the momentum-based PG methods.
  arXiv  Detail & Related papers  (2021-10-19T17:16:29Z)
• 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)
• Zeroth-order Deterministic Policy Gradient [116.87117204825105]
  We introduce Zeroth-order Deterministic Policy Gradient (ZDPG) ZDPG approximates policy-reward gradients via two-point evaluations of the $Q$function. New finite sample complexity bounds for ZDPG improve upon existing results by up to two orders of magnitude.
  arXiv  Detail & Related papers  (2020-06-12T16:52:29Z)
• Stochastic Recursive Momentum for Policy Gradient Methods [28.277961340108313]
  We propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (Storm-PG) Storm-PG enjoys a provably sharp $O (1/epsilon3)$ sample bound for STORM-PG, matching the best-known convergence rate for policy gradient algorithm. Numerical experiments depicts the superiority of our algorithm over comparative policy gradient algorithms.
  arXiv  Detail & Related papers  (2020-03-09T17:59:03Z)
• A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning [32.91450388566405]
  We develop a new Proximal Hybrid Policy Gradient Algorithm (ProxHSPGA) We prove that both algorithms can achieve the best-known trajectory complexity $mathcalOleft(varepsilon-4right)$ We evaluate the performance of our algorithm on several well-known examples in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-01T07:45:51Z)

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.