Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate

• URL: http://arxiv.org/abs/2403.00675v1
• Date: Fri, 1 Mar 2024 17:08:30 GMT
• Title: Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate
• Authors: Yifan Lin, Yuhao Wang, Enlu Zhou
• Abstract summary: We study a variant of the natural policy reusing historical trajectories via importance gradient sampling. We show that the bias of the proposed estimator of gradient sampling is gradientally negligible, the resultant algorithm is convergent, and reusing past trajectories helps improve the convergence rate.
• Score: 8.943964058164257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization of historical trajectories obtained from previous policies is essential for expediting policy optimization. Empirical evidence has shown that policy gradient methods based on importance sampling work well. However, existing literature often neglect the interdependence between trajectories from different iterations, and the good empirical performance lacks a rigorous theoretical justification. In this paper, we study a variant of the natural policy gradient method with reusing historical trajectories via importance sampling. We show that the bias of the proposed estimator of the gradient is asymptotically negligible, the resultant algorithm is convergent, and reusing past trajectories helps improve the convergence rate. We further apply the proposed estimator to popular policy optimization algorithms such as trust region policy optimization. Our theoretical results are verified on classical benchmarks.

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)
• Truncating Trajectories in Monte Carlo Reinforcement Learning [48.97155920826079]
  In Reinforcement Learning (RL), an agent acts in an unknown environment to maximize the expected cumulative discounted sum of an external reward signal. We propose an a-priori budget allocation strategy that leads to the collection of trajectories of different lengths. We show that an appropriate truncation of the trajectories can succeed in improving performance.
  arXiv  Detail & Related papers  (2023-05-07T19:41:57Z)
• Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality [94.89246810243053]
  This paper studies offline policy learning, which aims at utilizing observations collected a priori to learn an optimal individualized decision rule. Existing policy learning methods rely on a uniform overlap assumption, i.e., the propensities of exploring all actions for all individual characteristics must be lower bounded. We propose Pessimistic Policy Learning (PPL), a new algorithm that optimize lower confidence bounds (LCBs) instead of point estimates.
  arXiv  Detail & Related papers  (2022-12-19T22:43:08Z)
• Variance Reduction based Experience Replay for Policy Optimization [3.0657293044976894]
  We propose a general variance reduction based experience replay (VRER) framework that can selectively reuse the most relevant samples to improve policy gradient estimation. Our theoretical and empirical studies show that the proposed VRER can accelerate the learning of optimal policy and enhance the performance of state-of-the-art policy optimization approaches.
  arXiv  Detail & Related papers  (2022-08-25T20:51:00Z)
• Bag of Tricks for Natural Policy Gradient Reinforcement Learning [87.54231228860495]
  We have implemented and compared strategies that impact performance in natural policy gradient reinforcement learning. The proposed collection of strategies for performance optimization can improve results by 86% to 181% across the MuJuCo control benchmark.
  arXiv  Detail & Related papers  (2022-01-22T17:44:19Z)
• Variance Reduction based Experience Replay for Policy Optimization [3.0790370651488983]
  Variance Reduction Experience Replay (VRER) is a framework for the selective reuse of relevant samples to improve policy gradient estimation. VRER forms the foundation of our sample efficient off-policy learning algorithm known as Policy Gradient with VRER.
  arXiv  Detail & Related papers  (2021-10-17T19:28:45Z)
• Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient [34.16700176918835]
  Off-policy Reinforcement Learning holds the promise of better data efficiency. Current off-policy policy gradient methods either suffer from high bias or high variance, delivering often unreliable estimates. We propose a nonparametric Bellman equation, which can be solved in closed form.
  arXiv  Detail & Related papers  (2020-10-27T13:40:06Z)
• Efficient Policy Learning from Surrogate-Loss Classification Reductions [65.91730154730905]
  We consider the estimation problem given by a weighted surrogate-loss classification reduction of policy learning. We show that, under a correct specification assumption, the weighted classification formulation need not be efficient for policy parameters. We propose an estimation approach based on generalized method of moments, which is efficient for the policy parameters.
  arXiv  Detail & Related papers  (2020-02-12T18:54:41Z)
• A Nonparametric Off-Policy Policy Gradient [32.35604597324448]
  Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. We build on the general sample efficiency of off-policy algorithms. We show that our approach has better sample efficiency than state-of-the-art policy gradient methods.
  arXiv  Detail & Related papers  (2020-01-08T10:13:08Z)

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.