Skip to content
RobotWorld
← Back to Videos

AlphaNIST: One Policy From Scratch Solves All 20 NIST Assembly Tasks

Loading video
Loading video

A single policy trained from scratch with one binary reward completes 10 NIST assembly tasks in a row; OmniReset resets plus SGS task sampling enable multi-task training.

Robotic ArmManipulationReinforcement LearningAssembly
Category: arm
Author: @patrickhyin
Date: 2026-10-13T00:00:00
Duration: 6.8s
Source: https://x.com/patrickhyin/status/2110093031693250699
Reference: https://alpha-nist.github.io

Related Videos

AlphaNIST: Binary Reward Plus Control Cost Hits 98.2% Sim Success
1:33

AlphaNIST: Binary Reward Plus Control Cost Hits 98.2% Sim Success

@octi_zhang · 92 views · 2026-10-13
Robotic ArmManipulationReinforcement Learning
ACCRUE: Continual Off-Policy RL for Robot Foundation Models
1:00

ACCRUE: Continual Off-Policy RL for Robot Foundation Models

@cykim1006 · 32 views · 2026-10-14
Reinforcement LearningContinual learningRobot foundation models
AlphaNIST: Chaining Ten Robotic Assemblies from Sparse Rewards
0:10

AlphaNIST: Chaining Ten Robotic Assemblies from Sparse Rewards

@mateoguaman · 110 views · 2026-10-13
AlphaNISTReinforcement LearningRobotic Assembly
Pi API Enters Beta: Fine-Tune Pi Models for Customer Robots
0:40

Pi API Enters Beta: Fine-Tune Pi Models for Customer Robots

@chelseabfinn · 65 views · 2026-10-13
Robotic ArmDual-ArmPhysical Intelligence
Jev drives a MuJoCo metal arm with nine typed decisions
0:36

Jev drives a MuJoCo metal arm with nine typed decisions

@IsaacSin12 · 680 views · 2026-09-18
Robotic ArmManipulationMuJoCo
GPT-Policy: Dual-Arm Manipulation Learned In-Context from Demos
0:54

GPT-Policy: Dual-Arm Manipulation Learned In-Context from Demos

@z_code68632 · 865 views · 2026-09-15
In-Context LearningVLMManipulation

As an Amazon Associate, we earn from qualifying purchases.