Functional Critic Modeling for Provably Convergent Off-Policy Actor-Critic

• URL: http://arxiv.org/abs/2509.22964v2
• Date: Tue, 14 Oct 2025 20:20:33 GMT
• Title: Functional Critic Modeling for Provably Convergent Off-Policy Actor-Critic
• Authors: Qinxun Bai, Yuxuan Han, Wei Xu, Zhengyuan Zhou,
• Abstract summary: We introduce a novel concept of functional critic modeling, which leads to a new AC framework.<n>We provide a theoretical analysis in the linear function setting, establishing the provable convergence of our framework.
• Score: 29.711769434073755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Off-policy reinforcement learning (RL) with function approximation offers an effective way to improve sample efficiency by reusing past experience. Within this setting, the actor-critic (AC) framework has achieved strong empirical success. However, both the critic and actor learning is challenging for the off-policy AC methods: first of all, in addition to the classic "deadly triad" instability of off-policy evaluation, it also suffers from a "moving target" problem, where the policy being evaluated changes continually; secondly, actor learning becomes less efficient due to the difficulty of estimating the exact off-policy policy gradient. The first challenge essentially reduces the problem to repeatedly performing off-policy evaluation for changing policies. For the second challenge, the off-policy policy gradient theorem requires a complex and often impractical algorithm to estimate an additional emphasis critic, which is typically neglected in practice, thereby reducing to the on-policy policy gradient as an approximation. In this work, we introduce a novel concept of functional critic modeling, which leads to a new AC framework that addresses both challenges for actor-critic learning under the deadly triad setting. We provide a theoretical analysis in the linear function setting, establishing the provable convergence of our framework, which, to the best of our knowledge, is the first convergent off-policy target-based AC algorithm. From a practical perspective, we further propose a carefully designed neural network architecture for the functional critic modeling and demonstrate its effectiveness through preliminary experiments on widely used RL tasks from the DeepMind Control Benchmark.

Related papers

• Q-learning with Adjoint Matching [58.78551025170267]
  We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm.<n>QAM sidesteps two challenges by leveraging adjoint matching, a recently proposed technique in generative modeling.<n>It consistently outperforms prior approaches on hard, sparse reward tasks in both offline and offline-to-online RL.
  arXiv  Detail & Related papers  (2026-01-20T18:45:34Z)
• Quasi-Newton Compatible Actor-Critic for Deterministic Policies [2.745166507489733]
  We propose a second-order deterministic actor-critic framework in reinforcement learning.<n>We introduce a quadratic critic that simultaneously preserves the true policy gradient and an approximation of the performance Hessian.
  arXiv  Detail & Related papers  (2025-11-12T17:49:02Z)
• Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning [66.4260157478436]
  We study reinforcement learning in the policy learning setting.<n>The goal is to find a policy whose performance is competitive with the best policy in a given class of interest.
  arXiv  Detail & Related papers  (2025-07-06T14:40:05Z)
• Offline Reinforcement Learning with On-Policy Q-Function Regularization [57.09073809901382]
  We deal with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy. We propose two algorithms taking advantage of the estimated Q-function through regularizations, and demonstrate they exhibit strong performance on the D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T21:38:08Z)
• Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees [12.259191000019033]
  Actor-critic (AC) methods are widely used in reinforcement learning (RL) We design a joint objective for training the actor and critic in a decision-aware fashion. We empirically demonstrate the benefit of our decision-aware actor-critic framework on simple RL problems.
  arXiv  Detail & Related papers  (2023-05-24T15:34:21Z)
• 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)
• Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic [137.04558017227583]
  Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. We take a mean-field perspective on the evolution and convergence of feature-based neural AC. We prove that neural AC finds the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2021-12-27T06:09:50Z)
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction [73.77593805292194]
  We train a separate exploration policy to maximize an approximate upper confidence bound of the critics in an off-policy actor-critic framework. To mitigate the off-policy-ness, we adapt the recently introduced DICE framework to learn a distribution correction ratio for off-policy actor-critic training.
  arXiv  Detail & Related papers  (2021-10-22T22:07:51Z)
• Learning Value Functions in Deep Policy Gradients using Residual Variance [22.414430270991005]
  Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. Traditional actor-critic algorithms do not succeed in fitting the true value function. We provide a new state-value (resp. state-action-value) function approximation that learns the value of the states relative to their mean value.
  arXiv  Detail & Related papers  (2020-10-09T08:57:06Z)
• DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning [95.60782037764928]
  We show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step. Third, we show that ideas in the propensity estimation literature can be used to importance-sample transitions from replay buffer and update policy to prevent deterioration of performance.
  arXiv  Detail & Related papers  (2020-06-26T20:21:12Z)
• How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization [10.424426548124696]
  We propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients. MAGE backpropagates through the learned dynamics to compute gradient targets in temporal difference learning. We demonstrate the efficiency of the algorithm in comparison to model-free and model-based state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-04-29T16:30:53Z)

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.