---
_id: '7223'
abstract:
- lang: eng
  text: 'Tendon-driven robotic fingers are underactuated and strongly nonlinear, and
    their unidirectional, friction-attenuated tendon tension imposes actuation constraints
    that any practical controller must respect. A previous study established that
    a deterministic learning controller (DDPG) can track a grasp trajectory for such
    a finger and compared it against model-based schemes. The present work extends
    that line of investigation by asking a narrower but unresolved question: for this
    same single-actuator, three-link tendon-driven architecture, how does a deterministic
    actor-critic policy (DDPG) compare with a stochastic, maximum-entropy policy (SAC)
    once a tension-limit penalty is built directly into the learning objective? Using
    the previously validated physics-based simulation model, both agents are trained
    under identical conditions with a reward that jointly penalizes tracking error
    and tension-constraint violation, and are evaluated across random, sinusoidal,
    and step disturbances using steady-state error, RMS, ISE, and IAE. The results
    show a consistent and interpretable trade-off: the stochastic SAC policy attains
    lower tracking error and better disturbance rejection, especially under time-varying
    and abrupt loads, at the cost of noisier control and longer training, whereas
    the deterministic DDPG policy converges faster and produces smoother torque and
    tension profiles but adapts less well to coupled disturbances. The study isolates
    the role of the exploration mechanism and the tension penalty in shaping these
    behaviors and offers practical guidance on selecting between deterministic and
    stochastic actor-critic methods for physically constrained, underactuated tendon-driven
    systems.'
author:
- first_name: Kanat
  full_name: Suleimenov, Kanat
  last_name: Suleimenov
- first_name: Roza
  full_name: Beisembekova, Roza
  last_name: Beisembekova
- first_name: Beibit
  full_name: Abdikenov, Beibit
  last_name: Abdikenov
- first_name: Aiman
  full_name: Ozhikenova, Aiman
  last_name: Ozhikenova
- first_name: Assylbek
  full_name: Ozhiken, Assylbek
  last_name: Ozhiken
- first_name: Akim
  full_name: Kapsalyamov, Akim
  id: '257451'
  last_name: Kapsalyamov
  orcid: 0000-0003-3700-6214
  orcid_put_code_url: https://api.orcid.org/v2.0/0000-0003-3700-6214/work/230936086
date_created: 2026-10-19T11:45:29Z
date_updated: 2026-10-22T14:28:50Z
doi: 10.37943/CVPA1758
intvolume: '        27'
issue: '3'
language:
- iso: eng
main_file_link:
- open_access: '1'
oa: '1'
page: 138-151
publication: Scientific Journal of Astana IT University
publication_identifier:
  eissn:
  - 2707-904X
  issn:
  - 2707-9031
publication_status: published
publisher: Astana IT University
status: public
title: 'DEEP REINFORCEMENT LEARNING CONTROL OF A TENSION-CONSTRAINED TENDON-DRIVEN
  UNDERACTUATED ROBOTIC FINGER: A COMPARATIVE STUDY OF DDPG AND SAC'
tmp:
  image: /images/cc_by_nc_nd.png
  legal_code_url: https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode
  name: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
    (CC BY-NC-ND 4.0)
  short: CC BY-NC-ND (4.0)
type: journal_article
user_id: '220548'
volume: 27
year: '2026'
...