Assistax provides fast JAX-based assistive robotics environments with trainable humanoid partners, and shows current RL baselines have a coordination gap when facing unseen human preferences.
Component Formula Default Interpretation / Sweep Speed prefer- ence Pref(v; [vmin, vmax]) [0.06,0.14]m/s Rewards motion within the preferred speed range
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics
Assistax provides fast JAX-based assistive robotics environments with trainable humanoid partners, and shows current RL baselines have a coordination gap when facing unseen human preferences.