Our Latest Research on Transfer Learning in Noisy Environments Published!

Fri, 04 Oct 2024 00:00:00 +0000

We’re excited to share that our study, “Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze,” has been published in Sensors!

In this study, we delve into the critical challenge of noise in reinforcement learning environments. Specifically, we focus on how transfer learning algorithms—Predecessor and Successor Features (PFs and SFs)—perform in spatial learning tasks under noisy conditions.

Why Is This Study Important?

Noise is a significant factor in real-world applications, especially for systems that rely on accurate sensor data to make decisions. Our study provides valuable insights into how learning models can be optimized in such conditions by fine-tuning hyperparameters like the reward learning rate and eligibility trace decay. We discovered that these parameters significantly influence the agent’s adaptability and learning efficiency, providing practical guidelines for improving the performance of sensor-driven systems in noisy, dynamic environments.

Key Takeaways from Our Study:

We evaluated the impact of various hyperparameters on adaptive behavior in noisy spatial learning environments using a T-maze, revealing their critical role in learning efficiency.
We introduced a framework based on PF and SF to compare and quantify sensitivity to noise and adaptation in reinforcement learning models.
We identified the most robust hyperparameter configurations that optimize performance in noisy and variable conditions, providing practical insights for improving system adaptability.

This research offers valuable contributions to the fields of sensor systems, robotics, and autonomous navigation by enhancing learning models’ resilience to noise.

Read the full paper here to learn more! Additionally, the code used in the study can be accessed here.

My new paper just disclosed in preprint arXiv server.

Thu, 04 Nov 2021 00:00:00 +0000

Preprint for “The effect of synaptic weight initialization in feature-based successor representation learning” was just disclosed.

This paper explores the learning efficiency according to the weight initialization method in feature-based SR learning and discusses from neurobiological perspectives.

My new paper just disclosed.

Tue, 25 Aug 2020 00:00:00 +0000

I just published my paper at arXiv.

I’m happy to finish my paper.

This is the link for my paper.

I already posted about the result of the paper as conference poster in my blog, check this.

Neuromatch 2.0 poster

Wed, 20 May 2020 00:00:00 +0000

[pdf-embedder url=“neuromatch_slideposter.pdf”]

Research | NeuroAI Lab

Our Latest Research on Transfer Learning in Noisy Environments Published!

My new paper just disclosed in preprint arXiv server.

My new paper just disclosed.

Neuromatch 2.0 poster