mlsanityData to 14 Oct 2026

Generating Realistic Arm Movements in Reinforcement Learning: A Quantitative Comparison of Reward Terms and Task Requirements

arXiv 2402.13949 ↗First posted 21 Feb 2024cs.ROcited by 1

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

The mimicking of human-like arm movement characteristics involves the consideration of three factors during control policy synthesis: (a) chosen task requirements, (b) inclusion of noise during movement execution and (c) chosen optimality principles. Previous studies showed that when considering these factors (a-c) individually, it is possible to synthesize arm movements that either kinematically match the experimental data or reproduce the stereotypical triphasic muscle activation pattern. However, to date no quantitative comparison has been made on how realistic the arm movement generated by each factor is; as well as whether a partial or total combination of all factors results in arm movements with human-like kinematic characteristics and a triphasic muscle pattern. To investigate this, we used reinforcement learning to learn a control policy for a musculoskeletal arm model, aiming to discern which combination of factors (a-c) results in realistic arm movements according to four frequently reported stereotypical characteristics. Our findings indicate that incorporating velocity and acceleration requirements into the reaching task, employing reward terms that encourage minimization of mechanical work, hand jerk, and control effort, along with the inclusion of noise during movement, leads to the emergence of realistic human arm movements in reinforcement learning. We expect that the gained insights will help in the future to better predict desired arm movements and corrective forces in wearable assistive devices.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 23 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

5 of 23 references.

References · 5

  1. 2018Maximum a Posteriori Policy Optimisationcited by 328
  2. 2022DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systemscited by 29
  3. 2020Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarkingcited by 19
  4. 2020Reinforcement Learning Control of a Biomechanical Model of the Upper Extremitycited by 11
  5. 2023Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Modelscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MyoInteract: A Framework for Fast Prototyping of Biomechanical HCI Tasks using Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025KINESIS: Motion Imitation for Human Musculoskeletal Locomotion
  2. 2025Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning
  3. 2025Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics
  4. 2026Lambda-Hold Control: Human-Like Movement Emerges from a Minimal Task Reward in Predictive Musculoskeletal Simulation
  5. 2026Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning
  6. 2024Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows
  7. 2025Arnold: A multi-task, multi-embodiment muscle transformer policy
  8. 2025Embodied Learning of Reward for Musculoskeletal Control with Vision Language Models