GCR-PPO is a modification of PPO for multi-objective robot RL that: - uses a multi-head critic to obtain per-reward advantages and gradients, - applies priority-aware gradient surgery (PCGrad-style projection) to protect task objectives from regularisers, - runs at massively parallel GPU scale within IsaacLab/RSL-RL.
☆43Feb 13, 2026Updated 9 months ago
Alternatives and similar repositories for GCR-PPO
Users that are interested in GCR-PPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Extension of RSL-RL for using Morphological Symmetries in IsaacLab☆34Nov 4, 2026Updated 2 weeks ago
- ☆60Oct 10, 2025Updated last year
- Extension of RSL-RL for using Mixture-of-Experts in IsaacLab☆12Updated this week
- Algorithm implementation for our paper: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics☆60Jan 26, 2026Updated 9 months ago
- Code for our ICRA 2024 paper on learning diverse skills☆26Apr 6, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- code for SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control☆17May 26, 2025Updated last year
- Integrating Constraints in PPO (using Isaac Gym or Isaac Lab)☆176Sep 1, 2025Updated last year
- This is an official GitHub Repository for paper "Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcem…☆232Nov 30, 2025Updated 11 months ago
- The implementation of "Bi-level motion imitation for humanoid robots"☆13Jun 25, 2025Updated last year
- Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets☆202Apr 14, 2025Updated last year
- LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators (IROS'24)☆104Feb 6, 2025Updated last year
- Official Implementation of "PLT:Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters" (SIGGRAPH 2025)☆32Sep 3, 2025Updated last year
- Learning Agile Quadrupedal Locomotion on Challenging Terrains☆91Apr 11, 2024Updated 2 years ago
- Successfully scratching the scripts of mujoco code in the lined with H2O method, actually testing pending☆27May 25, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [Humanoids 2024 award finalist] Online DNN-Driven Nonlinear MPC for Stylistic Humanoid Robot Walking with Step Adjustment☆21Feb 5, 2025Updated last year
- IsaacLab to Mujoco GO2 deploy, IsaacLab to Real world GO2 deploy☆72Sep 9, 2025Updated last year
- This project contains a framework that allows the quadruped robot to explore and adapt to the open wild environment in a safe manner.☆60Dec 26, 2025Updated 10 months ago
- ☆175May 5, 2025Updated last year
- ☆37May 14, 2025Updated last year
- ☆148Nov 7, 2024Updated 2 years ago
- ☆18Mar 2, 2025Updated last year
- RAMBO: RL-augmented Model-based Whole-body Control for Loco-manipulation☆124Jul 23, 2025Updated last year
- Quadruped Tasks extension based on Isaac Lab.☆59Feb 23, 2026Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ARC Humanoid Robot Training for Isaac Lab☆13Jul 25, 2025Updated last year
- ☆21Oct 28, 2025Updated last year
- ☆73Updated this week
- Robust Reinforcement Learning-Based Locomotion for Resource-Constrained Quadrupeds with Exteroceptive Sensing☆130Oct 2, 2025Updated last year
- An IsaacLab DirectEnv for basic quadrupedal locomotion tasks, with support for multiple quadruped robots, sim-to-sim, and sim-to-real pip…☆143Updated this week
- ☆19Aug 28, 2025Updated last year
- Official Code for "Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning"☆159May 16, 2025Updated last year
- ☆119Nov 10, 2026Updated last week
- IsaacLab rl locomotion env benchmark with sim2real robustness guarantees.☆22Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Official implementation of HEAD CoRL 2025☆27Aug 22, 2025Updated last year
- ☆167Jul 10, 2026Updated 4 months ago
- A legged robots learning library based on IsaacLab☆33Feb 20, 2025Updated last year
- ☆11Feb 26, 2024Updated 2 years ago
- Learning Model for Aggressive Jumping Maneuvers☆32Mar 5, 2025Updated last year
- [ICLR 2024] Official code of the paper "Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts.☆51Nov 18, 2024Updated 2 years ago
- [arXiv 2025] ResMimic: From General Motion Tracking to Humanoid Whole-Body Loco-Manipulation via Residual Learning☆83Mar 24, 2026Updated 7 months ago
Are these results useful?