# Stabilizing Policy Gradient Methods via Reward Profiling

arXiv: https://arxiv.org/abs/2511.16629 · HTML: https://mlsanity.com/paper/2511.16629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Gradient Descent Finds Global Minima of Deep Neural Networks](https://mlsanity.com/paper/1811.03804/) (2018)
- [An Empirical Model of Large-Batch Training](https://mlsanity.com/paper/1812.06162/) (2018)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Neural Policy Gradient Methods: Global Optimality and Rates of Convergence](https://mlsanity.com/paper/1909.01150/) (2019)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation](https://mlsanity.com/paper/1708.05144/) (2017)
- [On the Convergence Rates of Policy Gradient Methods](https://mlsanity.com/paper/2201.07443/) (2022)
- [Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control](https://mlsanity.com/paper/1708.04133/) (2017)
- [Implicit Regularization in Deep Learning](https://mlsanity.com/paper/1709.01953/) (2017)
- [On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation](https://mlsanity.com/paper/1910.08412/) (2019)
- [Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms](https://mlsanity.com/paper/2005.03557/) (2020)
- [Trust Region-Guided Proximal Policy Optimization](https://mlsanity.com/paper/1901.10314/) (2019)
- [On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning](https://mlsanity.com/paper/1911.08250/) (2019)
- [Beyond variance reduction: Understanding the true impact of baselines on policy optimization](https://mlsanity.com/paper/2008.13773/) (2020)
- [Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives](https://mlsanity.com/paper/2002.12493/) (2020)
- [A Small Gain Analysis of Single Timescale Actor Critic](https://mlsanity.com/paper/2203.02591/) (2022)
- [Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic](https://mlsanity.com/paper/2301.12083/) (2023)
- [Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?](https://mlsanity.com/paper/2312.04548/) (2023)
- [Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees](https://mlsanity.com/paper/2202.00048/) (2022)
- [Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation](https://mlsanity.com/paper/2406.01762/) (2024)
- [Stochastic Variance Reduction for Policy Gradient Estimation](https://mlsanity.com/paper/1710.06034/) (2017)
- [The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations](https://mlsanity.com/paper/2401.13662/) (2024)

## Built on by (most cited first, 1 of 1)

- [Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning](https://mlsanity.com/paper/2610.02190/) (2026)

## Abstract (arXiv)

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.