Aidar Shakerimov

Aidar Shakerimov

Auto-generated profile, based on publicly available information

Aidar Shakerimov

Department of Robotics, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 December 2023 in IEEE Access
Verified
Journal Article
Open access
ASAidar Shakerimov
Aidar Shakerimov
TATohid Alizadeh
Tohid Alizadeh
HVHuseyin Atakan Varol
Huseyin Atakan Varol
Reinforcement learning has gained significant interest in modern industries for its advancements in tackling challenging control tasks compared to rule-based programs. However, the robustness aspect of this technique is still under development, limiting its widespread adoption. This problem has become more pronounced as users switch to training simulations to reduce costs, resulting in a reality gap that negatively affects real-world performance. One popular method employed to mitigate this problem is randomizing uncertain parameters of the environment during training. Nevertheless, this approach requires expert knowledge to determine the appropriate range of randomization. On the other hand, there is a technique that introduces fine-tuning of agents by adapting their policies to new environments. However, it is challenging to adapt policies when the new environment requires shifting them off their initial distribution. These obstacles limit the practical utilization and popularization of both techniques. Our study proposes a hybrid approach that handles these issues by fine-tuning agents trained with domain randomization through additional real-world training. To assess the efficacy of our approach, we conducted experiments involving a rotary inverted pendulum, augmented with an extra weight not represented in the simulation. Additionally, we employed simulated environments including a cart pole, a simple pendulum, a quadruped, and an ant robot scenario. These environments were given in two distinct versions with mismatching parameters to imitate a gap between training and testing conditions. The results demonstrate that adding as few as twenty to fifty additional real-world training episodes can significantly enhance the performance of agents trained with domain randomization. Moreover, including fifty to two hundred additional episodes can elevate it to a level comparable to those fully trained in the real world. Our study concludes that achieving efficient simulation-to-reality transfer is feasible with domain randomization and relatively small amounts of real-world training.

13 March 2023
Verified
Conference Paper
Open access
SSShamil Sarmonov
Shamil Sarmonov
ASAidar Shakerimov
Aidar Shakerimov
AAArna Aimysheva
Arna Aimysheva
AAAida Amirova
Aida Amirova
NONurziya Oralbayeva
Nurziya Oralbayeva
ASAnara Sandygulova
Anara Sandygulova
This works addresses the lately initiated Cyrillic-to-Latin alphabet shift in Kazakhstan that may bring challenges for early literacy development and acquisition; both public and scientific communities agree on possible resistance to acquiring and using a new alphabet. To support the acquisition of the new Kazakh Latin alphabet and its handwriting, this study proposes a reinforcement-learning (RL) system named QWriter. It comprises a humanoid robot NAO, a tablet with a stylus, and an RL agent that learns from a child's mistakes and progresses to maximize alphabet learning in the shortest amount of time by altering the order of practice words in response to a child's mistakes. We conducted a five-sessions experiment using a between-subject design with 69 Kazakh children ages 7 to 10 and compared their learning performance with a human tutor to assess the effectiveness of the QWriter system. Overall results show no significant differences in learning gains between the two conditions. Our study foregrounds the promising potential of the RL-based social robot in teaching foundational letter acquisition and writing over time.

19 April 2023
Verified
Conference Paper
Open access
ASAidar Shakerimov
Aidar Shakerimov
SSShamil Sarmonov
Shamil Sarmonov
AAAida Amirova
Aida Amirova
NONurziya Oralbayeva
Nurziya Oralbayeva
AZAida Zhanatkyzy
Aida Zhanatkyzy
ASAnara Sandygulova
Anara Sandygulova
In Kazakhstan, the ongoing Cyrillic-to-Latin alphabet shift raises challenges for early literacy development and acquisition in the Kazakh language. This paper proposes the QWriter system to help young children learn the Latin-based Kazakh alphabet and its handwriting. The system consists of a humanoid robot NAO, a tablet with a stylus, and a Reinforcement Learning (RL) agent that learns a child’s mistakes and progress to maximize alphabet learning in the shortest period of time by adapting the order of practice words according to the child’s mistakes. To evaluate the effectiveness of the QWriter system, we conducted a between-subject design experiment with 59 Kazakh children aged 6-8 years old and compared their learning performance with a human tutor and the CoWriting Kazakh robot system. The results did not support our assumption, we found that the proposed system received significantly higher likability scores than the baseline human tutor.