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.
Learning robust perceptive locomotion for quadrupedal robots in the wild
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
A framework using 3D Gaussian Splatting for visual domain randomization enables robust monocular RGB-based dexterous in-hand reorientation on real hardware for multiple objects under varied lighting.
Integrating foot position maps into heightmaps and adding a locomotion-stability reward in an attention-based RL framework improves quadrupedal success rates on both trained and out-of-domain complex terrains.
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.
Tuned foot compliance in quadruped robots lowers locomotion energy consumption by roughly 17 percent relative to rigid or overly soft designs.
Develops and tests a model-based RL controller with post-training for gait in a tendon-driven soft quadruped, reporting improved efficiency and robustness over benchmarks.
Swarm robots navigate unknown environments using goal direction and neighbor positions only, with mathematical validation, potential-field simulations, and sound-field robot experiments.
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.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
A framework using 3D Gaussian Splatting for visual domain randomization enables robust monocular RGB-based dexterous in-hand reorientation on real hardware for multiple objects under varied lighting.
-
Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards
Integrating foot position maps into heightmaps and adding a locomotion-stability reward in an attention-based RL framework improves quadrupedal success rates on both trained and out-of-domain complex terrains.
-
Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.
-
Energy-Efficient Quadruped Locomotion with Compliant Feet
Tuned foot compliance in quadruped robots lowers locomotion energy consumption by roughly 17 percent relative to rigid or overly soft designs.
-
Optimal Gait Control for a Tendon-driven Soft Quadruped Robot by Model-based Reinforcement Learning
Develops and tests a model-based RL controller with post-training for gait in a tendon-driven soft quadruped, reporting improved efficiency and robustness over benchmarks.
-
Power in Numbers: Primitive Algorithm for Swarm Robot Navigation in Unknown Environments
Swarm robots navigate unknown environments using goal direction and neighbor positions only, with mathematical validation, potential-field simulations, and sound-field robot experiments.