The paper introduces health-conditioned VLA models that incorporate a health vector via a new projector module and train on 128 malfunction episodes in the LIBERO simulator to complete tasks despite degraded joints.
Robots that can adapt like animals
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
GAME is a new adversarial coevolutionary QD algorithm using generational alternation and vision embeddings that outperforms one-sided baselines across battle, wrestling, and deck-building tasks while revealing arms-race dynamics and the role of neutral mutations.
Lamarckian evolution outperforms Darwinian on task performance alone but drops more sharply when morphological novelty is added, because reduced parent-offspring similarity weakens the value of inherited learned controllers.
RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.
citing papers explorer
-
Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control
The paper introduces health-conditioned VLA models that incorporate a health vector via a new projector module and train on 128 malfunction episodes in the LIBERO simulator to complete tasks despite degraded joints.
-
Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites
GAME is a new adversarial coevolutionary QD algorithm using generational alternation and vision embeddings that outperforms one-sided baselines across battle, wrestling, and deck-building tasks while revealing arms-race dynamics and the role of neutral mutations.
-
Limits of Lamarckian Evolution Under Pressure of Morphological Novelty
Lamarckian evolution outperforms Darwinian on task performance alone but drops more sharply when morphological novelty is added, because reduced parent-offspring similarity weakens the value of inherited learned controllers.
-
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.