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

Loading video

Telekinesis releases RLbotics, an open-source GPU-accelerated reinforcement learning library for robotics with multi-environment training across IsaacLab, MJLab, and Gymnasium.

RLbotics 强化学习 reinforcement learning 开源库 IsaacLab MJLab Gymnasium Telekinesis 机器人训练 Twitter

Category: research

Author: @telekinesis_ai

Date: 2026-08-13T00:00:00

Duration: 15.84s

Source: https://x.com/telekinesis_ai/status/2087797749076926845

Reference: https://github.com/telekinesis-ai/telekinesis-rlbotics

Why Reward-Based RL Is Extremely Sample Inefficient

Why Reward-Based RL Is Extremely Sample Inefficient

@cybernetic_lab · 10 views · 2026-07-31

强化学习reinforcement learningsample efficiency

Imitation + reinforcement learning for robust towel folding

Imitation + reinforcement learning for robust towel folding

@SciRobotics · 6 views · 2026-07-22

模仿学习imitation learning强化学习

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

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

@jayjunleee · 9 views · 2026-08-20

ADEPT灵巧手灵巧操作

Marope: multi-agent RL for robot rope jumping

Marope: multi-agent RL for robot rope jumping

@ErenChenAI · 6 views · 2026-08-12

多智能体强化学习机器人协同

FACT: Learning from failure in robot learning

FACT: Learning from failure in robot learning

@QuanquanPeng03 · 11 views · 2026-08-12

具身智能Embodied AI机器人学习

OpenAI sim-trained robot hand solves Rubiks cube

OpenAI sim-trained robot hand solves Rubiks cube

@GoDrift_ai · 9 views · 2026-08-11

灵巧手sim-to-real模拟训练