Proceedings Article10.1109/irc55401.2022.00022
GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks
01 Dec 2022
8
TL;DR: In this article , a genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (GA+DDPG+HER) was proposed to find values for the learning parameters that are close to optimal.
read more
Abstract: Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Survey on Deep Reinforcement Learning Algorithms for Robotic Manipulation
Dong-Ki Han,Ben Mulyana,Vladimir Stankovic,S. Cheng +3 more
TL;DR: A review of the recent advances in deep reinforcement learning algorithms for robotic manipulation tasks can be found in this article , where the authors outline the fundamental ideas of reinforcement learning and the parts of a reinforcement learning system.
Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey
TL;DR: A survey of this emerging trend in deep neuroevolution and deep Reinforcement Learning by organizing the literature into related groups of works and casting all the existing combinations in each group into a generic framework.
Deep Learning Hyperparameter Optimization for Breast Mass Detection in Mammograms
TL;DR: In this paper , the authors presented GA-E2E, a new approach for tuning the hyperparameters of DL models for breast cancer detection using Genetic Algorithms (GAs).
Research of Improved TD3 Robotic Arm Path Planning using Evolutionary Algorithm
Feng Zhang,Jianqiang Xiong,Shuai Yuan,Wen Kong +3 more
- 19 Aug 2023
TL;DR: Improved TD3 robotic arm path planning using evolutionary algorithm achieves high accuracy and fast training speed.
1
Deep Deterministic Policy Gradient Algorithm: A Systematic Review
Ebrahim Hamid Sumiea,Said Jadid AbdulKadir,Safwan Mahmood Al-Selwi,Alawi Alqushaibi,Mohammed Gamal Ragab,Suliman Mohamed Fati,Hitham Alhussian +6 more
- 06 Nov 2023
TL;DR: A systematic review of Deep Deterministic Policy Gradient (DDPG) algorithm focusing on its key concepts, applications, and comparisons with other algorithms.
1
References
•Proceedings Article
Continuous control with deep reinforcement learning
Timothy P. Lillicrap,Jonathan J. Hunt,Alexander Pritzel,Nicolas Heess,Tom Erez,Yuval Tassa,David Silver,Daan Wierstra +7 more
- 22 Jul 2016
TL;DR: In this paper, an actor-critic, model-free algorithm based on the deterministic policy gradient is proposed to operate over continuous action spaces, which is able to find policies whose performance is competitive with those found by a planning algorithm with full access to the dynamics of the domain.
6.5K
Lidar-Monocular Visual Odometry with Genetic Algorithm for Parameter Optimization.
Adarsh Sehgal,Ashutosh Singandhupe,Hung Manh La,Alireza Tavakkoli,Sushil J. Louis +4 more
- 07 Oct 2019
TL;DR: The use of Genetic Algorithm to optimize parameters with reference to LIMO and maximize LIMO's localization and motion estimation performance is argued and it is shown that the genetic algorithm helps LIMO to reduce translation error in different datasets.
17
Automatic Parameter Optimization Using Genetic Algorithm in Deep Reinforcement Learning for Robotic Manipulation Tasks
07 Apr 2022
TL;DR: In this paper , the authors proposed a Deep Deterministic Policy Gradient (DDPG) and Hindsight Experience Replay (HER) based method, which makes use of the Genetic Algorithm (GA) to fine-tune the hyperparameters' values.
AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay
23 Oct 2022
TL;DR: In this paper , a multi-actor-critic DDPG is proposed to enhance the performance and stability of actor and critic learning by using the average value of multiple actors or critics to substitute the single actor or critic.