pathak22/noreward-rl

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

51
/ 100
Established

This project helps AI researchers train intelligent agents in environments where external rewards are scarce or completely absent. It takes an agent and an environment, and outputs an agent capable of exploring and learning tasks primarily driven by an internal sense of 'curiosity.' This is ideal for researchers working on advanced AI for games, robotics, or complex simulations.

1,471 stars. No commits in the last 6 months.

Use this if you are an AI researcher experimenting with reinforcement learning agents in challenging environments that provide very few or no explicit rewards.

Not ideal if you are looking for a plug-and-play solution for environments with clear and frequent reward signals, or if you are not an AI/ML researcher.

reinforcement-learning AI-research agent-training sparse-rewards curiosity-driven-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,471

Forks

302

Language

Python

License

Last pushed

Dec 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pathak22/noreward-rl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.