zchuning/repo
Resilient Model-Based RL by Regularizing Posterior Predictability
This project helps robotics engineers and researchers develop AI agents that can perform tasks reliably, even when their environment is noisy or unpredictable. It takes raw visual data from a robotic setup and outputs robust control policies that guide the robot's actions. The end-user is typically someone working on robotic control, automation, or reinforcement learning research who needs agents to maintain performance despite visual distractions.
No commits in the last 6 months.
Use this if you are building AI agents for robotic control and need them to operate consistently in visually complex or changing environments, like those with video distractors or varied backgrounds.
Not ideal if you are working with symbolic AI, traditional control systems, or if your primary concern is not resilience to visual distractors in reinforcement learning.
Stars
22
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zchuning/repo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild