Cover Image

FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Seo, Younggyo, Sferrazza, Carmelo, Geng, Haoran, Nauman, Michal, Yin, Zhao-Heng, Abbeel, Pieter
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
by: Seo, Younggyo, et al.
Published: (2025)

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
by: Seo, Younggyo, et al.
Published: (2024)

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
by: Sferrazza, Carmelo, et al.
Published: (2024)

RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains
by: Zhang, Yuanhang, et al.
Published: (2026)

Body Transformer: Leveraging Robot Embodiment for Policy Learning
by: Sferrazza, Carmelo, et al.
Published: (2024)

Offline Imitation Learning Through Graph Search and Retrieval
by: Yin, Zhao-Heng, et al.
Published: (2024)

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
by: Sukhija, Bhavya, et al.
Published: (2024)

Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
by: Jones, Joshua, et al.
Published: (2025)

Visual Representation Learning with Stochastic Frame Prediction
by: Jang, Huiwon, et al.
Published: (2024)

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
by: Yang, Lujie, et al.
Published: (2025)

GaussGym: An open-source real-to-sim framework for learning locomotion from pixels
by: Escontrela, Alejandro, et al.
Published: (2025)

Continuous Control with Coarse-to-fine Reinforcement Learning
by: Seo, Younggyo, et al.
Published: (2024)

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
by: Kim, Dongyoung, et al.
Published: (2023)

Object-centric 3D Motion Field for Robot Learning from Human Videos
by: Yin, Zhao-Heng, et al.
Published: (2025)

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
by: Wu, Zhen, et al.
Published: (2026)

Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields
by: Yin, Zhao-Heng, et al.
Published: (2025)

Hand-Object Interaction Pretraining from Videos
by: Singh, Himanshu Gaurav, et al.
Published: (2024)

ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation
by: Heng, Liang, et al.
Published: (2025)

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
by: Nauman, Michal, et al.
Published: (2025)

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
by: Lee, Vint, et al.
Published: (2023)

Flow Policy Gradients for Robot Control
by: Yi, Brent, et al.
Published: (2026)

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
by: Kim, Dongyoung, et al.
Published: (2025)

Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
by: Li, Zhongyu, et al.
Published: (2024)

FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators
by: Tao, Heng, et al.
Published: (2026)

From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
by: Shentu, Yide, et al.
Published: (2024)

When Does Non-Uniform Replay Matter in Reinforcement Learning?
by: Korniak, Michal, et al.
Published: (2026)

Reward-Conditioned Reinforcement Learning
by: Nauman, Michal, et al.
Published: (2026)

Twisting Lids Off with Two Hands
by: Lin, Toru, et al.
Published: (2024)

How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference
by: Lin, Toru, et al.
Published: (2026)

ZeroWBC: Learning Natural Visuomotor Humanoid Control Directly from Human Egocentric Video
by: Yang, Haoran, et al.
Published: (2026)

SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
by: Kuang, Yuxuan, et al.
Published: (2025)

I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning
by: Yan, Yashuai, et al.
Published: (2024)

MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
by: Liu, Fangchen, et al.
Published: (2024)

Learning from Massive Human Videos for Universal Humanoid Pose Control
by: Mao, Jiageng, et al.
Published: (2024)

TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control
by: Zhuang, Zifeng, et al.
Published: (2025)

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
by: Jang, Huiwon, et al.
Published: (2025)

Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments
by: He, Xiaoyi, et al.
Published: (2025)

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
by: Kim, Changyeon, et al.
Published: (2025)

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
by: Eschmann, Jonas, et al.
Published: (2023)

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
by: Jang, Huiwon, et al.
Published: (2024)