Performance Variation in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2606.06746v1
• Date: Thu, 04 Jun 2026 21:59:47 GMT
• Title: Performance Variation in Deep Reinforcement Learning
• Abstract summary: This paper outlines the limitations of conventional uncertainty and variation estimates.<n>We then propose an alternative percentile-based statistic and visualization method.<n>These tools are easy to interpret and rely on standard properties of sample percentiles.
• Score: 8.399817109063038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep reinforcement learning (RL) algorithms often suffer from low run-to-run robustness, manifesting as significant performance variation across independent runs of identically configured agents. Although this issue poses a spectrum of challenges across research and practice, relatively few studies develop methods to evaluate it; RL research instead often reports uncertainty in the estimated mean performance. In this paper, we outline the limitations of conventional uncertainty and variation estimates, particularly their misalignment with purpose and the risk of underreporting. We then propose an alternative percentile-based statistic and visualization method, min-max IPR and run-wise percentile highlighting, respectively. These percentile-based tools are easy to interpret and rely on standard properties of sample percentiles, providing rich information about run-to-run performance variation. We demonstrate this through three case studies. First, we show that LayerNorm and penultimate-layer normalizations narrow performance variation in PPO, whereas the variation is mostly unchanged in SAC. Second, we compare PPO, SAC, TD-MPC, and TD-MPC2, and show TD-MPC exhibits the least variation while being the most data efficient among the four. Finally, in a comparison of DQN and Rainbow on five Atari environments, we show that both algorithms exhibit similar levels of performance variation.

Related papers

• What are Key Factors for Updates in RL for LLM Reasoning? [41.37684066124904]
  We show that differences in off-policy degree, determined by the number of gradient steps per rollout, substantially affect the distribution of importance sampling ratios and their clipping behavior.<n>Motivated by these findings, we propose Adaptive Clip Policy Optimization (ACPO), which clipping boundaries across token groups according to the empirical variance of their importance sampling ratios.
  arXiv  Detail & Related papers  (2026-06-21T16:14:46Z)
• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms [0.0]
  This paper presents a study evaluating the performance of DT against traditional offline RL algorithms in dense and sparse reward settings.<n>We found that DTs showed less sensitivity to varying reward density compared to other methods.<n>Traditional value-based methods like IQL showed improved performance in dense reward settings with high-quality data, while CQL offered balanced performance across different data qualities.
  arXiv  Detail & Related papers  (2025-11-20T15:44:11Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms [14.82820088479196]
  Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. In this work, we contribute tools to perform such a comprehensive evaluation. We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time.
  arXiv  Detail & Related papers  (2024-05-27T14:03:28Z)
• Assessing the Impact of Distribution Shift on Reinforcement Learning Performance [0.0]
  Reinforcement learning (RL) faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to the optimal policy during training, may obfuscate overfitting or dependence on the experimental setup. We propose a set of evaluation methods that measure the robustness of RL algorithms under distribution shifts.
  arXiv  Detail & Related papers  (2024-02-05T23:50:55Z)
• Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning [57.83232242068982]
  Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. It remains unclear which attributes of DA account for its effectiveness in achieving sample-efficient visual RL. This work conducts comprehensive experiments to assess the impact of DA's attributes on its efficacy.
  arXiv  Detail & Related papers  (2023-05-25T15:46:20Z)
• Actor Prioritized Experience Replay [0.0]
  Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. We introduce a novel experience replay sampling framework for actor-critic methods, which also regards issues with stability and recent findings behind the poor empirical performance of PER. An extensive set of experiments verifies our theoretical claims and demonstrates that the introduced method significantly outperforms the competing approaches.
  arXiv  Detail & Related papers  (2022-09-01T15:27:46Z)
• ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention [48.697458429460184]
  Two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer. This paper proposes a well-designed model named ERNIE-Sparse. It consists of two distinctive parts: (i) Hierarchical Sparse Transformer (HST) to sequentially unify local and global information, and (ii) Self-Attention Regularization (SAR) to minimize the distance for transformers with different attention topologies.
  arXiv  Detail & Related papers  (2022-03-23T08:47:01Z)
• Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
  We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss. Experimental results show that our model defines a new state of the art for various datasets and settings.
  arXiv  Detail & Related papers  (2021-12-10T20:46:13Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Deep Reinforcement Learning at the Edge of the Statistical Precipice [31.178451465925555]
  We argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. We advocate for reporting interval estimates of aggregate performance and propose performance profiles to account for the variability in results.
  arXiv  Detail & Related papers  (2021-08-30T14:23:48Z)

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.