Accelerated Target Updates for Q-learning

2019-05-07 · Bowen Weng, Huaqing Xiong, Wei zhang

This paper studies accelerations in Q-learning algorithms. We propose an accelerated target update scheme by incorporating the historical iterates of Q functions. The idea is conceptually inspired by the momentum-based accelerated methods in the optimization theory. Conditions under which the proposed accelerated algorithms converge are established. The algorithms are validated using commonly adopted testing problems in reinforcement learning, including the FrozenLake grid world game, two discrete-time LQR problems from the Deepmind Control Suite, and the Atari 2600 games. Simulation results show that the proposed accelerated algorithms can improve the convergence performance compared with the vanilla Q-learning algorithm.

📄 PDF Abstract BibTeX arXiv:1905.02841

Code (0)

등록된 구현이 없습니다.

Tasks

Atari GamesQ-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

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} +…

GPU-GLMB: Assessing the Scalability of GPU-Accelerated Multi-Hypothesis Tracking

2025-12-06 · Pranav Balakrishnan, Sidisha Barik, Sean M. O'Rourke, Benjamin M. Marlin arxiv

Much recent research on multi-target tracking has focused on multi-hypothesis approaches leveraging random finite sets. Of particular interest are labeled random finite set methods that maintain temporally coherent label…

Accelerating Perturbed Stochastic Iterates in Asynchronous Lock-Free Optimization

2021-09-30 · Kaiwen Zhou, Anthony Man-Cho So, James Cheng

We show that stochastic acceleration can be achieved under the perturbed iterate framework (Mania et al., 2017) in asynchronous lock-free optimization, which leads to the optimal incremental gradient complexity for finit…

Stacking as Accelerated Gradient Descent

2024-03-08 · Naman Agarwal, Pranjal Awasthi, Satyen Kale, Eric Zhao

Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older layers, has proven quite successful in imp…

Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning

2018-02-19 · Qingkai Liang, Fanyu Que, Eytan Modiano

Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI

2026-08-19 · Heyang Thomas Li, Alexander Pletzer, Yuan Tian, Yi Mei 외 arxiv

Python is widely used in scientific research because it enables rapid development and provides rich ecosystems for data analysis, artificial intelligence (AI), and machine learning. However, customized research code can …