# Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.00329 · HTML: https://mlsanity.com/paper/2510.00329/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 3 of its 27 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 3 of 3)

- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control](https://mlsanity.com/paper/1909.04947/) (2019)
- [Cost Function Estimation Using Inverse Reinforcement Learning with Minimal Observations](https://mlsanity.com/paper/2505.08619/) (2025)

## Abstract (arXiv)

This paper investigates the application of Minimal Observation Inverse Reinforcement Learning (MO-IRL) to model and predict human arm-reaching movements with time-varying cost weights. Using a planar two-link biomechanical model and high-resolution motion-capture data from subjects performing a pointing task, we segment each trajectory into multiple phases and learn phase-specific combinations of seven candidate cost functions. MO-IRL iteratively refines cost weights by scaling observed and generated trajectories in the maximum entropy IRL formulation, greatly reducing the number of required demonstrations and convergence time compared to classical IRL approaches. Training on ten trials per posture yields average joint-angle Root Mean Squared Errors (RMSE) of 6.4 deg and 5.6 deg for six- and eight-segment weight divisions, respectively, versus 10.4 deg using a single static weight. Cross-validation on remaining trials and, for the first time, inter-subject validation on an unseen subject's 20 trials, demonstrates comparable predictive accuracy, around 8 deg RMSE, indicating robust generalization. Learned weights emphasize joint acceleration minimization during movement onset and termination, aligning with smoothness principles observed in biological motion. These results suggest that MO-IRL can efficiently uncover dynamic, subject-independent cost structures underlying human motor control, with potential applications for humanoid robots.