# vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement

arXiv: https://arxiv.org/abs/2405.08638 · HTML: https://mlsanity.com/paper/2405.08638/

## 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 28 of its 50 references that are in the map.
- First posted on arXiv 14 May 2024.

## 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, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research](https://mlsanity.com/paper/1802.09464/) (2018)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [Randomized Prior Functions for Deep Reinforcement Learning](https://mlsanity.com/paper/1806.03335/) (2018)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion](https://mlsanity.com/paper/1807.01675/) (2018)
- [SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning](https://mlsanity.com/paper/2007.04938/) (2020)
- [Maxmin Q-learning: Controlling the Estimation Bias of Q-learning](https://mlsanity.com/paper/2002.06487/) (2020)
- [Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.01929/) (2016)
- [Online Robust Reinforcement Learning with Model Uncertainty](https://mlsanity.com/paper/2109.14523/) (2021)
- [Better Exploration with Optimistic Actor-Critic](https://mlsanity.com/paper/1910.12807/) (2019)
- [Estimating Risk and Uncertainty in Deep Reinforcement Learning](https://mlsanity.com/paper/1905.09638/) (2019)
- [A Review of Uncertainty for Deep Reinforcement Learning](https://mlsanity.com/paper/2208.09052/) (2022)
- [i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops](https://mlsanity.com/paper/2207.06572/) (2022)
- [Selective Dyna-style Planning Under Limited Model Capacity](https://mlsanity.com/paper/2007.02418/) (2020)
- [Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2301.08502/) (2023)
- [Ensemble Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.02618/) (2023)
- [OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments](https://mlsanity.com/paper/2312.12145/) (2023)

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

- [Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling](https://mlsanity.com/paper/2507.00518/) (2025)

## Abstract (arXiv)

Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL.