Full-Gradient Successor Feature Representations

• URL: http://arxiv.org/abs/2604.00686v1
• Date: Wed, 01 Apr 2026 09:44:13 GMT
• Title: Full-Gradient Successor Feature Representations
• Abstract summary: Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL)<n>We propose Full-Gradient Successor Feature Representations Q-Learning (FG-SFRQL), an algorithm that optimize the successor features by minimizing the full Mean Squared Bellman Error.<n>We provide a theoretical proof of almost-sure convergence for FG-SFRQL and demonstrate empirically that minimizing the full residual leads to superior sample efficiency and transfer performance.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL) by decoupling environment dynamics from reward functions. However, standard SF learning methods typically rely on semi-gradient Temporal Difference (TD) updates. When combined with non-linear function approximation, semi-gradient methods lack robust convergence guarantees and can lead to instability, particularly in the multi-task setting where accurate feature estimation is critical for effective GPI. Inspired by Full Gradient DQN, we propose Full-Gradient Successor Feature Representations Q-Learning (FG-SFRQL), an algorithm that optimizes the successor features by minimizing the full Mean Squared Bellman Error. Unlike standard approaches, our method computes gradients with respect to parameters in both the online and target networks. We provide a theoretical proof of almost-sure convergence for FG-SFRQL and demonstrate empirically that minimizing the full residual leads to superior sample efficiency and transfer performance compared to semi-gradient baselines in both discrete and continuous domains.

Related papers

• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models [55.01951088768769]
  DiffusionOPD is a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD)<n>We show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-14T16:49:09Z)
• Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformation [12.18106607619171]
  The Reward Transformation framework was introduced to regret minimization to achieve last-iterate convergence.<n>We propose an adaptive technique to address these issues, ensuring better consistency between theoretical guarantees and practical performance.<n>Our methods significantly accelerate convergence, outperforming state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2025-09-17T02:58:20Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• Stochastic Primal-Dual Double Block-Coordinate for Two-way Partial AUC Maximization [45.99743804547533]
  Two-way partial AUCAUC is a critical performance metric for binary classification with imbalanced data.<n>Existing algorithms for TPAUC optimization remain under-explored.<n>We introduce two innovative double-coordinate block-coordinate algorithms for TPAUC optimization.
  arXiv  Detail & Related papers  (2025-05-28T03:55:05Z)
• Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation [28.63391989014238]
  Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time.<n>We propose a model-based algorithm that achieves both sample and computational efficiency.<n>We show that a near-optimal policy can be learned with a suboptimality gap of $tildeO(sqrtd_mathcalR + d_mathcalFN-1/2)$ using $N$ measurements.
  arXiv  Detail & Related papers  (2025-05-20T18:37:51Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Statistical Inference for Temporal Difference Learning with Linear Function Approximation [55.80276145563105]
  We investigate the statistical properties of Temporal Difference learning with Polyak-Ruppert averaging.<n>We make three theoretical contributions that improve upon the current state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-21T15:34:44Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning [9.202586157819693]
  quadratic methods for minimizing robustness for non composite objective functions typically rely on the Lipschitz smoothness of the differentiable part.<n>We propose a family of Bregman (SBPG) methods that only adaptivity.<n>MSBPG, a momentum-based variant, enhances convergence sensitivity by relaxing the minibatch size requirement.
  arXiv  Detail & Related papers  (2023-06-26T08:54:46Z)
• On Feature Learning in Neural Networks with Global Convergence Guarantees [49.870593940818715]
  We study the optimization of wide neural networks (NNs) via gradient flow (GF) We show that when the input dimension is no less than the size of the training set, the training loss converges to zero at a linear rate under GF. We also show empirically that, unlike in the Neural Tangent Kernel (NTK) regime, our multi-layer model exhibits feature learning and can achieve better generalization performance than its NTK counterpart.
  arXiv  Detail & Related papers  (2022-04-22T15:56:43Z)
• Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent [95.94432031144716]
  We propose a unified non- optimization framework for the analysis of a learning network. We show that existing guarantees can be trained unified through gradient descent.
  arXiv  Detail & Related papers  (2021-06-25T17:45:00Z)
• Robust Learning via Persistency of Excitation [4.674053902991301]
  We show that network training using gradient descent is equivalent to a dynamical system parameter estimation problem. We provide an efficient technique for estimating the corresponding Lipschitz constant using extreme value theory. Our approach also universally increases the adversarial accuracy by 0.1% to 0.3% points in various state-of-the-art adversarially trained models.
  arXiv  Detail & Related papers  (2021-06-03T18:49:05Z)
• An improved convergence analysis for decentralized online stochastic non-convex optimization [17.386715847732468]
  In this paper, we show that a technique called GT-Loakjasiewics (GT-Loakjasiewics) satisfies the existing condition GT-Loakjasiewics (GT-Loakjasiewics) satisfies the current best convergence rates. The results are not only immediately applicable but also the currently known best convergence rates.
  arXiv  Detail & Related papers  (2020-08-10T15:29:13Z)

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.