Analogical Reinforcement Learning With Two-Stage Memory Retrieval

2014 ◽  
Author(s):  
James Foster ◽  
Matt Jones
Keyword(s):  
Reinforcement Learning ◽  
Memory Retrieval ◽  
Two Stage

Living Object Grasping Using Two-Stage Graph Reinforcement Learning

2021 ◽  
Vol 6 (2) ◽  
pp. 1950-1957
Author(s):  
Zhe Hu ◽  
Yu Zheng ◽  
Jia Pan
Keyword(s):  
Reinforcement Learning ◽  
Two Stage

scholarly journals Two-Stage Pursuit Strategy for Incomplete-Information Impulsive Space Pursuit-Evasion Mission Using Reinforcement Learning

Aerospace ◽  
2021 ◽  
Vol 8 (10) ◽  
pp. 299
Author(s):  
Bin Yang ◽  
Pengxuan Liu ◽  
Jinglang Feng ◽  
Shuang Li
Keyword(s):  
Reinforcement Learning ◽  
Incomplete Information ◽  
Trajectory Optimization ◽  
Game Problem ◽  
Gradient Algorithm ◽  
Two Stage ◽  
Pursuit Evasion ◽  
Evasion Game ◽  
Close Distance ◽  
Pursuit Strategy

This paper presents a novel and robust two-stage pursuit strategy for the incomplete-information impulsive space pursuit-evasion missions considering the J2 perturbation. The strategy firstly models the impulsive pursuit-evasion game problem into a far-distance rendezvous stage and a close-distance game stage according to the perception range of the evader. For the far-distance rendezvous stage, it is transformed into a rendezvous trajectory optimization problem and a new objective function is proposed to obtain the pursuit trajectory with the optimal terminal pursuit capability. For the close-distance game stage, a closed-loop pursuit approach is proposed using one of the reinforcement learning algorithms, i.e., the deep deterministic policy gradient algorithm, to solve and update the pursuit trajectory for the incomplete-information impulsive pursuit-evasion missions. The feasibility of this novel strategy and its robustness to different initial states of the pursuer and evader and to the evasion strategies are demonstrated for the sun-synchronous orbit pursuit-evasion game scenarios. The results of the Monte Carlo tests show that the successful pursuit ratio of the proposed method is over 91% for all the given scenarios.

Postural Control of Two-Stage Inverted Pendulum Using Reinforcement Learning and Self-organizing Map

2007 ◽  
pp. 722-729
Author(s):  
Jae-kang Lee ◽  
Tae-seok Oh ◽  
Yun-su Shin ◽  
Tae-jun Yoon ◽  
Il-hwan Kim
Keyword(s):  
Reinforcement Learning ◽  
Postural Control ◽  
Inverted Pendulum ◽  
Self Organizing Map ◽  
Two Stage ◽  
Self Organizing

Two-stage reinforcement-learning-based cognitive radio with exploration control

2011 ◽  
Vol 5 (5) ◽  
pp. 644-651 ◽  
Author(s):  
T. Jiang ◽  
D. Grace ◽  
Y. Liu
Keyword(s):  
Reinforcement Learning ◽  
Cognitive Radio ◽  
Two Stage

A Two-Stage Reinforcement Learning Approach for Multi-UAV Collision Avoidance Under Imperfect Sensing

2020 ◽  
Vol 5 (2) ◽  
pp. 3098-3105
Author(s):  
Dawei Wang ◽  
Tingxiang Fan ◽  
Tao Han ◽  
Jia Pan
Keyword(s):  
Reinforcement Learning ◽  
Collision Avoidance ◽  
Learning Approach ◽  
Two Stage ◽  
Multi Uav ◽  
Imperfect Sensing

scholarly journals StackDRL: Stacked Deep Reinforcement Learning for Fine-grained Visual Categorization

2018 ◽  
Author(s):  
Xiangteng He ◽  
Yuxin Peng ◽  
Junjie Zhao
Keyword(s):  
Reinforcement Learning ◽  
Visual Information ◽  
Experimental Validation ◽  
State Of The Art ◽  
Two Stage ◽  
Visual Categorization ◽  
Fine Grained ◽  
Reward Function ◽  
Main Challenge ◽  
Labor Consumption

Fine-grained visual categorization (FGVC) is the discrimination of similar subcategories, whose main challenge is to localize the quite subtle visual distinctions between similar subcategories. There are two pivotal problems: discovering which region is discriminative and representative, and determining how many discriminative regions are necessary to achieve the best performance. Existing methods generally solve these two problems relying on the prior knowledge or experimental validation, which extremely restricts the usability and scalability of FGVC. To address the "which" and "how many" problems adaptively and intelligently, this paper proposes a stacked deep reinforcement learning approach (StackDRL). It adopts a two-stage learning architecture, which is driven by the semantic reward function. Two-stage learning localizes the object and its parts in sequence ("which"), and determines the number of discriminative regions adaptively ("how many"), which is quite appealing in FGVC. Semantic reward function drives StackDRL to fully learn the discriminative and conceptual visual information, via jointly combining the attention-based reward and category-based reward. Furthermore, unsupervised discriminative localization avoids the heavy labor consumption of labeling, and extremely strengthens the usability and scalability of our StackDRL approach. Comparing with ten state-of-the-art methods on CUB-200-2011 dataset, our StackDRL approach achieves the best categorization accuracy.

scholarly journals Exploration of genetic network programming with two-stage reinforcement learning for mobile robot

2019 ◽  
Vol 17 (3) ◽  
pp. 1447
Author(s):  
Siti Sendari ◽  
Arif Nur Afandi ◽  
Ilham Ari Elbaith Zaeni ◽  
Yogi Dwi Mahandi ◽  
Kotaro Hirasawa ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Mobile Robot ◽  
Genetic Network ◽  
Network Programming ◽  
Two Stage ◽  
Genetic Network Programming
Sign in / Sign up

Export Citation Format

Share Document