#强化学习 (70)

NaP-Control: Diffusion Prior for Fast Character Control

NaP-Control角色控制扩散先验强化学习全身控制

FACT: Learning from failure in robot learning

具身智能Embodied AI机器人学习Robot Learning失败学习

NVIDIA open-source humanoid controller training framework

人形机器人NVIDIA强化学习控制器开源

CMU open-sources the HTD whole-body controller for humanoids — playable in your browser

人形机器人全身控制Isaac LabUnitree G1强化学习

REGRIND: Dexterous RL from Human Retargeting Initialization

灵巧操作Dexterous ManipulationRL强化学习REGRIND

RL Framework Lets Robots Autonomously Choose Gait on Uneven Terrain

强化学习RL步态地形导航ScienceRobotics

PAC-MAN: Humanoid Dodges Balls for Whole-Body Safety

人形机器人安全强化学习PAC-MANhumanoid

Imitation + reinforcement learning for robust towel folding

模仿学习imitation learning强化学习reinforcement learning操控

FetchMan: Humanoid Loco-Manipulation from Simulation

人形具身智能Sim2Real移动操作强化学习

ADEPT: Sim Pre-training for Zero-Shot Visuo-Tactile Dexterity

ADEPT灵巧手灵巧操作视触觉触觉传感

Physics-Based Character Controllers with RL

强化学习物理角色控制RLcharacter controlneural_avb

Why Reward-Based RL Is Extremely Sample Inefficient

强化学习reinforcement learningsample efficiencyworld model奖励学习

OpenAI sim-trained robot hand solves Rubiks cube

灵巧手sim-to-real模拟训练OpenAI魔方

Marope: multi-agent RL for robot rope jumping

多智能体强化学习机器人协同Marope南京大学

WARL: Wrench-Augmented Reinforcement Learning (IROS 2026)

强化学习RL腿式机器人IROS2026Twitter

RL2-VLA: adaptive RL compositional steering framework

VLARL²-VLA测试时缩放强化学习OOD

RLbotics: Open-Source GPU-Accelerated RL Library for Robotics

RLbotics强化学习reinforcement learning开源库IsaacLab

FlexionAI: RGB-Based RL Policy Training in Simulation

强化学习RLRGBSim-to-real仿真

Fudan RoboMaster wheeled-legged robot uses end-to-end RL

轮腿机器人强化学习复旦RoboMasterWheeled-Legged

Multi-critic Learning for Whole-body End-effector Twist Tracking

强化学习全身控制多评论家末端执行器四足机器人

Learning Agile Navigation in Crowded Environments for Quadruped Robots

四足机器人quadruped导航navigation拥挤环境

HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning

人形Humanoid乒乓球Table Tennis全身控制

Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior

人形机器人多步态强化学习对抗运动先验爬楼梯

Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

世界模型DreamerKoopman谱约束强化学习

Humanoid Seated Locomotion on Passive Mobile Chair

人形机器人Humanoid坐姿移动Seated Locomotion控制策略

Learning Dynamic Pick-and-Place for a Legged Manipulator

腿式操作动态抓取强化学习拾取与放置四足机器人

SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning

步态优化人形机器人Koopman强化学习Reinforcement Learning

Offline RL with Hierarchical Action Chunking

强化学习动作分块离线RL人形机器人Paper

Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot

步态优化人形机器人轮滑强化学习Inline Skating

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

机器人智能体AgentOS智能体操作系统具身智能多模态记忆

PRIOR: Perceptive Learning for Humanoid Locomotion with Reference Gait Priors

人形机器人强化学习步态先验感知运动Isaac Lab

Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility

四足机器人运动先验强化学习运动模仿局部导航

Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking

人形机器人全身运动运动生成运动跟踪强化学习

Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion

人形机器人爬楼梯强化学习地形感知几何条件

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

VLA强化学习离线RL推理时引导测试时扩展

X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching

导航扩散策略强化学习跨本体NavDP

PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration

世界模型强化学习动作探索具身智能Paper

Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

LATENT人形机器人网球动作学习运动技能

Deep Reinforcement Learning for Adaptive Gain Tuning in Control of Teleoperation Manipulators with Joint Flexibility and Time-Varying Delays

Reinforcement Learning强化学习Paper

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

世界-动作模型端到端自动驾驶视频生成流匹配强化学习

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

VLA人形机器人humanoid全身控制whole-body

Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning

机器人操控强化学习行为克隆Q-Learning自改进

A Framework for Deploying Learning-based Quadruped Loco-Manipulation

四足操作强化学习sim-to-realROS开源框架

DELTA: Deformable Elevation-Based Local Terrain Attention Encoder for Sparse-Terrain Quadrupedal Locomotion

四足机器人四足运动强化学习地形感知注意力机制

LAC: Linear and Angular Compliance for Humanoid Whole-body Control

人形机器人全身控制柔顺控制导纳控制强化学习

AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance

人形机器人全身控制关键点引导强化学习运动控制

MLM: Learning Multi-task Loco-Manipulation Whole-Body Control for Quadruped Robot with Arm

强化学习移动操作四足机器人多任务全身控制

Learning Humanoid Standing-up Control across Diverse Postures

人形机器人强化学习起立控制sim-to-realUnitree-G1

Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation

足式机器人移动操作力位控制强化学习Unitree

LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks

Reinforcement Learning强化学习Paper

A Replay-Constrained Simulation Framework for Personalization of Powered Knee--Ankle Prosthesis Controllers

Reinforcement Learning强化学习Paper

Learning Humanoid Locomotion with Perceptive Internal Model

人形机器人感知内部模型强化学习复杂地形运动控制

The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL

世界模型持续学习强化学习Dreamer灾难性遗忘

CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots

人形机器人Unitree G1MoE对比学习地形适应

FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion

步态优化强化学习SACPlasticityHumanoidBench

Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation

腿式操作地形感知全身控制感知强化学习

CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation

人形机器人loco-manipulation灵巧操作强化学习行走操作

Expert Behavior Prior Reinforcement Learning

Reinforcement Learning强化学习Paper

Tac4Loco: Learning Spatiotemporal Plantar Pressure Representations for Humanoid Locomotion

人形机器人足底压力触觉感知运动控制强化学习

MoE-Loco: Mixture of Experts for Multitask Locomotion

混合专家多任务行走腿式机器人强化学习四足机器人

Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments

强化学习RL安全safetyCBF-QP

Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning

世界模型多智能体强化学习Dreamer通信

PRISM: Polynomial Representations for Interaction-Structured Motor Control

运动控制多项式网络人形机器人强化学习模仿学习

First Deployable Dynamic-CoM: A Unified Policy and Method-Agnostic Benchmark for Humanoid Single-Leg Balance

人形机器人单腿平衡动态质心xCoM强化学习

An offline approach to fNIRS-guided reinforcement learning for robot behavior

BCIfNIRS强化学习机器人控制Paper

ADEPT: Pre-Train Dexterity Once, Post-Train Every Task

灵巧操作强化学习sim-to-real预训练dexterous manipulation

Atlas' Evolution From Research Robot to Industrial Humanoid

Atlas波士顿动力人形机器人工业机器人Hyundai

Training a Humanoid Robot for Hard Work

Atlas波士顿动力强化学习RL人形机器人

Meta Open-Sources Project SuperDex: A Unified Dexterous Manipulation Platform with a Contact-First Physics Engine and Zero-Shot Sim2Real

Meta灵巧操作dexterous manipulation物理仿真physics engine

Can Football Teach a Robot to Move?

Atlas波士顿动力强化学习足球动作捕捉