Cover Image

Uncovering Latent Phase Structures and Branching Logic in Locomotion Policies: A Case Study on HalfCheetah

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yasui, Daisuke, Matsuki, Toshitaka, Sato, Hiroshi
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature Extension
by: Yasui, Daisuke, et al.
Published: (2026)

An accuracy-aware extension to LRP-based pruning for CNNs to prevent cascading accuracy degradation in data-scarce transfer learning
by: Yasui, Daisuke, et al.
Published: (2025)

Learning Quadruped Locomotion Policies using Logical Rules
by: DeFazio, David, et al.
Published: (2021)

Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots
by: Zheng, Ziang, et al.
Published: (2025)

LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation
by: Wang, Zhiquan, et al.
Published: (2026)

Latent Action Priors for Locomotion with Deep Reinforcement Learning
by: Hausdörfer, Oliver, et al.
Published: (2024)

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies
by: Chen, Zixuan, et al.
Published: (2024)

Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments
by: Angarola, Matheus P., et al.
Published: (2025)

Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
by: Nakanishi, Kosuke, et al.
Published: (2025)

Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion
by: Khandelwal, Nimesh, et al.
Published: (2026)

Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection
by: Cha, Junhyeok Rui, et al.
Published: (2026)

PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion
by: Ntagkas, Alexandros, et al.
Published: (2025)

Learning Quadruped Locomotion Using Differentiable Simulation
by: Song, Yunlong, et al.
Published: (2024)

A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion
by: Xue, Yufei, et al.
Published: (2025)

MoE-Loco: Mixture of Experts for Multitask Locomotion
by: Huang, Runhan, et al.
Published: (2025)

Variable Stiffness for Robust Locomotion through Reinforcement Learning
by: Spoljaric, Dario, et al.
Published: (2025)

Flexible Locomotion Learning with Diffusion Model Predictive Control
by: Huang, Runhan, et al.
Published: (2025)

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
by: Acero, Fernando, et al.
Published: (2024)

PRIOR: Perceptive Learning for Humanoid Locomotion with Reference Gait Priors
by: Han, Chenxi, et al.
Published: (2026)

PMG: Parameterized Motion Generator for Human-like Locomotion Control
by: Han, Chenxi, et al.
Published: (2026)

LocoFormer: Generalist Locomotion via Long-context Adaptation
by: Liu, Min, et al.
Published: (2025)

Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion
by: Coholich, Jeremiah, et al.
Published: (2025)

CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains
by: Zeng, Qixin, et al.
Published: (2026)

Learning to Walk with Less: a Dyna-Style Approach to Quadrupedal Locomotion
by: Affonso, Francisco, et al.
Published: (2025)

StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion
by: Ma, Le, et al.
Published: (2025)

MULE: Multi-terrain and Unknown Load Adaptation for Effective Quadrupedal Locomotion
by: Kurva, Vamshi Kumar, et al.
Published: (2025)

Robust Robot Walker: Learning Agile Locomotion over Tiny Traps
by: Zhu, Shaoting, et al.
Published: (2024)

Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
by: Jiang, Yicheng, et al.
Published: (2026)

SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion
by: Zhang, Zukun, et al.
Published: (2026)

Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Model
by: Lee, Minho, et al.
Published: (2026)

Reduced-Order Model-Guided Reinforcement Learning for Demonstration-Free Humanoid Locomotion
by: Liu, Shuai, et al.
Published: (2025)

No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
by: Dugar, Pranay, et al.
Published: (2025)

An Untethered Bioinspired Robotic Tensegrity Dolphin with Multi-Flexibility Design for Aquatic Locomotion
by: Zhao, Luyang, et al.
Published: (2024)

ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots
by: Shafiee, Milad, et al.
Published: (2023)

GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control
by: Wan, Hanwen, et al.
Published: (2025)

No More Blind Spots: Learning Vision-Based Omnidirectional Bipedal Locomotion for Challenging Terrain
by: Gadde, Mohitvishnu S., et al.
Published: (2025)

Proprioceptive External Torque Learning for Floating Base Robot and its Applications to Humanoid Locomotion
by: Lim, Daegyu, et al.
Published: (2023)

S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion
by: Li, Zimu, et al.
Published: (2026)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
by: Wang, Yiqi, et al.
Published: (2025)

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation
by: Zhang, Hao, et al.
Published: (2024)