Reliable Critics: Monotonic Improvement and Convergence Guarantees for Reinforcement Learning

• URL: http://arxiv.org/abs/2506.07134v1
• Date: Sun, 08 Jun 2025 13:27:11 GMT
• Title: Reliable Critics: Monotonic Improvement and Convergence Guarantees for Reinforcement Learning
• Authors: Eshwar S. R., Gugan Thoppe, Aditya Gopalan, Gal Dalal,
• Abstract summary: We introduce Reliable Policy Iteration (RPI)<n>RPI replaces the common projection or Bellman-error minimization during policy evaluation with a Bellman-based constrained optimization.<n>For practical use, we provide a model-free variant of RPI that amounts to a novel critic.
• Score: 18.316821694827734
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Despite decades of research, it remains challenging to correctly use Reinforcement Learning (RL) algorithms with function approximation. A prime example is policy iteration, whose fundamental guarantee of monotonic improvement collapses even under linear function approximation. To address this issue, we introduce Reliable Policy Iteration (RPI). It replaces the common projection or Bellman-error minimization during policy evaluation with a Bellman-based constrained optimization. We prove that not only does RPI confer textbook monotonicity on its value estimates but these estimates also lower bound the true return. Also, their limit partially satisfies the unprojected Bellman equation, emphasizing RPI's natural fit within RL. RPI is the first algorithm with such monotonicity and convergence guarantees under function approximation. For practical use, we provide a model-free variant of RPI that amounts to a novel critic. It can be readily integrated into primary model-free PI implementations such as DQN and DDPG. In classical control tasks, such RPI-enhanced variants consistently maintain their lower-bound guarantee while matching or surpassing the performance of all baseline methods.

Related papers

• Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient [18.64288030584699]
  heterogeneous multi-agent reinforcement learning (MARL)<n>Objectively replace the sequentially computed $Q_psi*(s,a_1:i)$ with the Optimal Marginal Q function $phi_psi*(s,a_1:i)$ derived from Q-functions.<n>Generalized Q Critic (GQC) as the critic function, employing pessimistic uncertainty-constrained loss to optimize different Q-value estimations.
  arXiv  Detail & Related papers  (2025-07-14T07:16:01Z)
• Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning [55.33984461046492]
  Policy-based methods currently dominate reinforcement learning pipelines for large language model (LLM) reasoning.<n>We introduce Trajectory Bellman Residual Minimization (TBRM), an algorithm that naturally adapts this idea to LLMs.<n>We prove convergence to the near-optimal KL-regularized policy from arbitrary off-policy via an improved change-of-trajectory-measure analysis.
  arXiv  Detail & Related papers  (2025-05-21T09:41:53Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [15.038210624870656]
  Reward inference is a critical intermediate step in the Reinforcement Learning from Human Feedback pipeline.<n>This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDP bandit, and general preference models beyond the Bradley-Terry model.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• 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)
• Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets [4.126347193869613]
  Upside-Down Reinforcement Learning (UDRL) is an approach for solving problems that does not require value functions. Goal-Conditional Supervised Learning (GCSL) optimized a lower bound on goal-reaching performance. This raises expectations that such algorithms may enjoy guaranteed convergence to the optimal policy in arbitrary environments.
  arXiv  Detail & Related papers  (2022-05-13T12:43:25Z)
• Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning [85.50033812217254]
  Actor-critic methods are widely used in offline reinforcement learning practice, but are not so well-understood theoretically. We propose a new offline actor-critic algorithm that naturally incorporates the pessimism principle.
  arXiv  Detail & Related papers  (2021-08-19T17:27:29Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking [59.691919635037216]
  Policy evaluation is a key process in Reinforcement Learning (RL) We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties.
  arXiv  Detail & Related papers  (2020-02-17T13:30:43Z)

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.