STRIDE: Learning Humanoid Locomotion in Minutes with Acceleration-Based Rewards
cs.RO, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Massively Scaling Explicit Policy-conditioned Value Functions
- Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
- Active Embodiment Identification with Reinforcement Learning for Legged Robots
- Rapid Embodiment Adaptation for Quadrupedal Locomotion
- Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation