# Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization

arXiv: https://arxiv.org/abs/1905.04100 · HTML: https://mlsanity.com/paper/1905.04100/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2019.

## Built on by (most cited first, 24 of 24)

- [Symbolic Regression via Neural-Guided Genetic Programming Population Seeding](https://mlsanity.com/paper/2111.00053/) (2021)
- [Automated Reinforcement Learning (AutoRL): A Survey and Open Problems](https://mlsanity.com/paper/2201.03916/) (2022)
- [Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey](https://mlsanity.com/paper/2203.14009/) (2022)
- [PopulAtion Parameter Averaging (PAPA)](https://mlsanity.com/paper/2304.03094/) (2023)
- [Rapid Motor Adaptation for Robotic Manipulator Arms](https://mlsanity.com/paper/2312.04670/) (2023)
- [Automated Reinforcement Learning: An Overview](https://mlsanity.com/paper/2201.05000/) (2022)
- [New Challenges in Reinforcement Learning: A Survey of Security and Privacy](https://mlsanity.com/paper/2301.00188/) (2022)
- [Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding](https://mlsanity.com/paper/2308.05893/) (2023)
- [Innovations in Integrating Machine Learning and Agent-Based Modeling of Biomedical Systems](https://mlsanity.com/paper/2206.01092/) (2022)
- [Evolutionary Reinforcement Learning: A Systematic Review and Future Directions](https://mlsanity.com/paper/2402.13296/) (2024)
- [ARLO: A Framework for Automated Reinforcement Learning](https://mlsanity.com/paper/2205.10416/) (2022)
- [Optimal Actor-Critic Policy with Optimized Training Datasets](https://mlsanity.com/paper/2108.06911/) (2021)
- [Balancing Profit, Risk, and Sustainability for Portfolio Management](https://mlsanity.com/paper/2207.02134/) (2022)
- [Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints](https://mlsanity.com/paper/2507.10131/) (2025)
- [Deep Learning Hyperparameter Optimization for Breast Mass Detection in Mammograms](https://mlsanity.com/paper/2207.11244/) (2022)
- [AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay](https://mlsanity.com/paper/2210.12892/) (2022)
- [A Semantic Modular Framework for Events Topic Modeling in Social Media](https://mlsanity.com/paper/2301.09009/) (2023)
- [Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice](https://mlsanity.com/paper/2405.11457/) (2024)
- [Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution](https://mlsanity.com/paper/2410.21940/) (2024)
- [Pulling the Carpet Below the Learner's Feet: Genetic Algorithm To Learn Ensemble Machine Learning Model During Concept Drift](https://mlsanity.com/paper/2412.09035/) (2024)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Quadratic speedup of global search using a biased crossover of two good solutions](https://mlsanity.com/paper/2111.07680/) (2021)
- [Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes](https://mlsanity.com/paper/2306.07741/) (2023)
- [Dual-Individual Genetic Algorithm: A Dual-Individual Approach for Efficient Training of Multi-Layer Neural Networks](https://mlsanity.com/paper/2504.17346/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) enables agents to take decision based on a reward function. However, in the process of learning, the choice of values for learning algorithm parameters can significantly impact the overall learning process. In this paper, we use a genetic algorithm (GA) to find the values of parameters used in Deep Deterministic Policy Gradient (DDPG) combined with Hindsight Experience Replay (HER), to help speed up the learning agent. We used this method on fetch-reach, slide, push, pick and place, and door opening in robotic manipulation tasks. Our experimental evaluation shows that our method leads to better performance, faster than the original algorithm.