Extending Differential Temporal Difference Methods for Episodic Problems

• URL: http://arxiv.org/abs/2605.04368v1
• Date: Wed, 06 May 2026 00:10:17 GMT
• Title: Extending Differential Temporal Difference Methods for Episodic Problems
• Abstract summary: Differential temporal difference (TD) methods are value-based reinforcement learning algorithms.<n>We study reward centering in episodic problems and propose a generalization of differential TD.<n>We show equivalence with a form of linear TD, thereby inheriting theoretical guarantees that have been shown for those algorithms.
• Score: 4.184451801360084
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. They rely on reward centering, where each reward is centered by the average reward. This keeps the return bounded and removes a value function's state-independent offset. However, reward centering can alter the optimal policy in episodic problems, limiting its applicability. Motivated by recent works that emphasize the role of normalization in streaming deep reinforcement learning, we study reward centering in episodic problems and propose a generalization of differential TD. We prove that this generalization maintains the ordering of policies in the presence of termination, and thus extends differential TD to episodic problems. We show equivalence with a form of linear TD, thereby inheriting theoretical guarantees that have been shown for those algorithms. We then extend several streaming reinforcement learning algorithms to their differential counterparts. Across a range of base algorithms and environments, we empirically validate that reward centering can improve sample efficiency in episodic problems.

Related papers

• Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes [19.67390261007849]
  Differential temporal difference (TD) learning algorithms are a major advance for average reward RL.<n>Existing convergence guarantees require a local clock in learning rates tied to state visit counts.<n>We prove the almost sure convergence of on-policy $n$-step differential TD for any $n$ using standard diminishing learning rates without a local clock.
  arXiv  Detail & Related papers  (2026-02-18T17:24:27Z)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward [8.445578144906415]
  We propose a novel episodic return decomposition method called Diaster. Diaster decomposes any episodic reward into credits of two divided sub-trajectories at any cut point. Experimental results show that our method outperforms previous state-of-the-art methods in terms of both sample efficiency and performance.
  arXiv  Detail & Related papers  (2023-12-17T07:58:19Z)
• Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees [56.848265937921354]
  Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy. Many algorithms for IRL have an inherently nested structure. We develop a novel single-loop algorithm for IRL that does not compromise reward estimation accuracy.
  arXiv  Detail & Related papers  (2022-10-04T17:13:45Z)
• Instance-Dependent Confidence and Early Stopping for Reinforcement Learning [99.57168572237421]
  Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. This research provides guarantees that explain textitex post the performance differences observed. A natural next step is to convert these theoretical guarantees into guidelines that are useful in practice.
  arXiv  Detail & Related papers  (2022-01-21T04:25:35Z)
• Anti-Concentrated Confidence Bonuses for Scalable Exploration [57.91943847134011]
  Intrinsic rewards play a central role in handling the exploration-exploitation trade-off. We introduce emphanti-concentrated confidence bounds for efficiently approximating the elliptical bonus. We develop a practical variant for deep reinforcement learning that is competitive with contemporary intrinsic rewards on Atari benchmarks.
  arXiv  Detail & Related papers  (2021-10-21T15:25:15Z)
• Can Q-learning solve Multi Armed Bantids? [0.0]
  We show that current reinforcement learning algorithms are not capable of solving Multi-Armed-Bandit problems. This stems from variance differences between policies, which causes two problems. We propose the Adaptive Symmetric Reward Noising (ASRN) method, by which we mean equalizing the rewards variance across different policies.
  arXiv  Detail & Related papers  (2021-10-21T07:08:30Z)
• Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning [50.44564503645015]
  We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. We prove tighter upper regret bounds for optimistic algorithms and accompany them with new information-theoretic lower bounds for a large class of MDPs.
  arXiv  Detail & Related papers  (2021-07-02T20:36:05Z)
• Emphatic Algorithms for Deep Reinforcement Learning [43.17171330951343]
  Temporal difference learning algorithms can become unstable when combined with function approximation and off-policy sampling. Emphatic temporal difference (ETD($lambda$) algorithm ensures convergence in the linear case by appropriately weighting the TD($lambda$) updates. We show that naively adapting ETD($lambda$) to popular deep reinforcement learning algorithms, which use forward view multi-step returns, results in poor performance.
  arXiv  Detail & Related papers  (2021-06-21T12:11:39Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)
• Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning [9.359939442911127]
  This paper focuses on resetting variational inequalities (VI) under Markovian noise. A prominent application of our algorithmic developments is the policy evaluation problem in reinforcement learning.
  arXiv  Detail & Related papers  (2020-11-15T04:05:22Z)
• Policy Gradient for Continuing Tasks in Non-stationary Markov Decision Processes [112.38662246621969]
  Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. We compute unbiased navigation gradients of the value function which we use as ascent directions to update the policy. A major drawback of policy gradient-type algorithms is that they are limited to episodic tasks unless stationarity assumptions are imposed.
  arXiv  Detail & Related papers  (2020-10-16T15:15:42Z)

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.