Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning

• URL: http://arxiv.org/abs/2511.10843v1
• Date: Thu, 13 Nov 2025 23:06:40 GMT
• Title: Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
• Authors: Alexander W. Goodall, Edwin Hamel-De le Court, Francesco Belardinelli,
• Abstract summary: We show that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates.<n>We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved.
• Score: 52.97053840476386
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we leverage new results from off-policy evaluation; it has recently been shown that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates. This result is surprising as it means collecting data on-policy is not variance optimal. We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved to learn optimal policies. Off-policy RL has been well studied (e.g., IMPALA), with correct and truncated importance weighted samples for de-biasing and managing variance appropriately. Generally these approaches are concerned with reconciling data collected from multiple workers in parallel, while the policy is updated asynchronously, mismatch between the workers and policy is corrected in a mathematically sound way. Here we consider only one worker - the behaviour policy, which is used to collect data for policy improvement, with provably lower variance return estimates. In our experiments we extend two policy-gradient methods with this regime, demonstrating better sample efficiency and performance over a diverse set of environments.

Related papers

• ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm [2.6813717321945103]
  We propose a new PPO variant based on the stability guarantee from conservative on-policy iteration with a more efficient off-policy data utilization.<n>Compared with PPO and some other state-of-the-art variants, we demonstrate an improved performance of ExO-PPO with balanced sample efficiency and stability on varied tasks.
  arXiv  Detail & Related papers  (2026-02-10T12:29:57Z)
• EXPO: Stable Reinforcement Learning with Expressive Policies [74.30151915786233]
  We propose a sample-efficient online reinforcement learning algorithm to maximize value with two parameterized policies.<n>Our approach yields up to 2-3x improvement in sample efficiency on average over prior methods.
  arXiv  Detail & Related papers  (2025-07-10T17:57:46Z)
• Doubly Optimal Policy Evaluation for Reinforcement Learning [16.7091722884524]
  Policy evaluation often suffers from large variance and requires massive data to achieve desired accuracy.<n>In this work, we design an optimal combination of data-collecting policy and data-processing baseline.<n>Theoretically, we prove our doubly optimal policy evaluation method is unbiased and guaranteed to have lower variance than previously best-performing methods.
  arXiv  Detail & Related papers  (2024-10-03T05:47:55Z)
• 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)
• On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling [3.5253513747455303]
  We introduce an adaptive, off-policy sampling method to improve the data efficiency of on-policy policy gradient algorithms. Our method, Proximal Robust On-Policy Sampling (PROPS), reduces sampling error by collecting data with a behavior policy.
  arXiv  Detail & Related papers  (2023-11-14T16:37:28Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Iteratively Refined Behavior Regularization for Offline Reinforcement Learning [57.10922880400715]
  In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. By iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks.
  arXiv  Detail & Related papers  (2023-06-09T07:46:24Z)
• 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.<n>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.<n>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)
• Latent-Variable Advantage-Weighted Policy Optimization for Offline RL [70.01851346635637]
  offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios. We propose to leverage latent-variable policies that can represent a broader class of policy distributions. Our method improves the average performance of the next best-performing offline reinforcement learning methods by 49% on heterogeneous datasets.
  arXiv  Detail & Related papers  (2022-03-16T21:17:03Z)

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.