paper-with-me

Papers

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

2022-06-20 · Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $\epsilon$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing additional bias. Specifically, we design a dual architecture consisting of two branches, one of which is a copy of DQN, namely the Q-branch. The other branch, which we call the preference branch, learns the action preference that the DQN implicit follows. We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values. Consequently, preference-guided $\epsilon$-greedy exploration motivates the DQN agent to take diverse actions, i.e., actions with larger Q-values can be sampled more frequently whereas actions with smaller Q-values still have a chance to be explored, thus encouraging the exploration. We assess the proposed method with four well-known DQN variants in nine different environments. Extensive results confirm the superiority of our proposed method in terms of performance and convergence speed. Index Terms- Preference-guided exploration, stochastic policy, data efficiency, deep reinforcement learning, deep Q-learning.

📄 PDF Abstract BibTeX arXiv:2206.09627

Code (1)

OscarHuangWind/Preference-Guided-DQN-Atari 공식 구현 pytorch

Tasks

Atari GamesDeep Reinforcement LearningQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Epsilon Greedy Exploration 설명 없음
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling

2026-03-01 · Jiachen Yang, Xianhui Lin, Yi Dong, Zebiao Zheng 외 arxiv

Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Superv…

Reinforcement LearningImage Editing

PGDQN: Preference-Guided Deep Q-Network

2023-10-03 · IEEE Transactions on Neural Networks and Learning Systems 2023 10 · Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He 외

Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm. However, most existing stochastic exploration approaches either explore actions heuristically regardless of their Q-values or couple…

Atari GamesBenchmarkingEfficient ExplorationQ-Learning+1

Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics

2026-02-04 · Ruizhe Zhong, Jiesong Lian, Xiaoyue Mi, Zixiang Zhou 외 arxiv

While online Reinforcement Learning has emerged as a crucial technique for aligning flow matching models with human preferences, current approaches are hindered by inefficient exploration during training rollouts. Relyin…

Text-to-Video GenerationReinforcement Learning

Fine-Grained GRPO for Precise Preference Alignment in Flow Models

2025-10-02 · Yujie Zhou, Pengyang Ling, Jiazi Bu, Yibin Wang 외 arxiv

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveragi…

Reinforcement Learning

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

2026-01-01 · Shengjun Zhang, Zhang Zhang, Chensheng Dai, Yueqi Duan arxiv

Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existing methods which optimize over multiple …

Reinforcement Learning