Gradient Iterated Temporal-Difference Learning

• URL: http://arxiv.org/abs/2603.07833v1
• Date: Sun, 08 Mar 2026 22:32:15 GMT
• Title: Gradient Iterated Temporal-Difference Learning
• Abstract summary: Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes.<n>Most approaches in this paradigm implement a semi-gradient update to boost the learning speed.<n> gradient TD methods were introduced to overcome this issue, but have not been widely used.
• Score: 31.96531765414569
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the gradient of the bootstrapped estimate. While popular, this type of update is prone to divergence, as Baird's counterexample illustrates. Gradient TD methods were introduced to overcome this issue, but have not been widely used, potentially due to issues with learning speed compared to semi-gradient methods. Recently, iterated TD learning was developed to increase the learning speed of TD methods. For that, it learns a sequence of action-value functions in parallel, where each function is optimized to represent the application of the Bellman operator over the previous function in the sequence. While promising, this algorithm can be unstable due to its semi-gradient nature, as each function tracks a moving target. In this work, we modify iterated TD learning by computing the gradients over those moving targets, aiming to build a powerful gradient TD method that competes with semi-gradient methods. Our evaluation reveals that this algorithm, called Gradient Iterated Temporal-Difference learning, has a competitive learning speed against semi-gradient methods across various benchmarks, including Atari games, a result that no prior work on gradient TD methods has demonstrated.

Related papers

• Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion [2.1301560294088318]
  Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL)<n>We propose implicit TD algorithms that reformulate TD updates into fixed point equations.<n>Our results show that implicit TD algorithms are applicable to a much broader range of step sizes.
  arXiv  Detail & Related papers  (2025-05-02T15:57:54Z)
• Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation [12.732028509861829]
  We study policy evaluation problems in multi-task reinforcement learning (RL) under a low-rank representation setting.<n>We propose a new variant of TD learning method, where we integrate the so-called truncated singular value decomposition step into the update of TD learning.<n>Our empirical results show that the proposed method significantly outperforms the classic TD learning, where the performance gap increases as the rank $r$ decreases.
  arXiv  Detail & Related papers  (2025-03-03T20:07:45Z)
• Class Gradient Projection For Continual Learning [99.105266615448]
  Catastrophic forgetting is one of the most critical challenges in Continual Learning (CL) We propose Class Gradient Projection (CGP), which calculates the gradient subspace from individual classes rather than tasks.
  arXiv  Detail & Related papers  (2023-11-25T02:45:56Z)
• ELRA: Exponential learning rate adaption gradient descent optimization method [83.88591755871734]
  We present a novel, fast (exponential rate), ab initio (hyper-free) gradient based adaption. The main idea of the method is to adapt the $alpha by situational awareness. It can be applied to problems of any dimensions n and scales only linearly.
  arXiv  Detail & Related papers  (2023-09-12T14:36:13Z)
• Bridging Discrete and Backpropagation: Straight-Through and Beyond [62.46558842476455]
  We propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. We propose ReinMax, which achieves second-order accuracy by integrating Heun's method, a second-order numerical method for solving ODEs.
  arXiv  Detail & Related papers  (2023-04-17T20:59:49Z)
• Toward Efficient Gradient-Based Value Estimation [4.365720395124051]
  Gradient-based methods for value estimation in reinforcement learning are typically much slower than Temporal Difference (TD) learning methods. We study the root causes of this slowness and show that Mean Square Bellman Error (MSBE) is an ill-conditioned loss function in the sense that its Hessian has large condition-number. We propose a low complexity batch-free proximal method that approximately follows the Gauss-Newton direction and is robust to parameterization. Our main algorithm, called RANS, is efficient in the sense that it is significantly faster than the residual gradient methods while having almost the same
  arXiv  Detail & Related papers  (2023-01-31T16:45:49Z)
• One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning [61.662504399411695]
  We introduce a novel method mixing multiple inner steps that enjoys a more accurate and robust meta-gradient signal. When applied to the Snake game, the mixing meta-gradient algorithm can cut the variance by a factor of 3 while achieving similar or higher performance.
  arXiv  Detail & Related papers  (2021-10-30T08:36:52Z)
• Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization [89.66571637204012]
  textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing.
  arXiv  Detail & Related papers  (2021-06-22T03:13:23Z)
• Correcting Momentum in Temporal Difference Learning [95.62766731469671]
  We argue that momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale. We show that this phenomenon exists, and then propose a first-order correction term to momentum. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.
  arXiv  Detail & Related papers  (2021-06-07T20:41:15Z)
• Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity [40.73281056650241]
  We introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true gradient temporal difference learning algorithms. We show how gradient TD reinforcement learning methods can be formally derived, not by starting from their original objective functions, as previously attempted, but rather from a primal-dual saddle-point objective function.
  arXiv  Detail & Related papers  (2020-06-06T21:04:21Z)
• Variance Reduction with Sparse Gradients [82.41780420431205]
  Variance reduction methods such as SVRG and SpiderBoost use a mixture of large and small batch gradients. We introduce a new sparsity operator: The random-top-k operator. Our algorithm consistently outperforms SpiderBoost on various tasks including image classification, natural language processing, and sparse matrix factorization.
  arXiv  Detail & Related papers  (2020-01-27T08:23:58Z)

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.