ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
Guillaume Bellegarda, Milad Shafiee, and Auke Ijspeert
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SRL combines SLIP feedforward with RL feedback to produce stable bipedal and quadrupedal jumps with lower training cost than pure RL.
Neuromechanical digital twins embed neural controllers in simulated bodies to infer unmeasurable biophysical variables, generate testable hypotheses via perturbations, and bridge neuroscience with robotics and machine learning.
citing papers explorer
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping
SRL combines SLIP feedforward with RL feedback to produce stable bipedal and quadrupedal jumps with lower training cost than pure RL.
-
The embodied brain: Bridging the brain, body, and behavior with neuromechanical digital twins
Neuromechanical digital twins embed neural controllers in simulated bodies to infer unmeasurable biophysical variables, generate testable hypotheses via perturbations, and bridge neuroscience with robotics and machine learning.