LukasSchaefer/MSc_Curiosity_MARL
MSc Informatics dissertation project - University of Edinburgh: Curiosity in Multi-Agent Reinforcement Learning
This project helps researchers and developers working on complex AI systems to understand how 'curiosity' influences the learning process of multiple AI agents. It takes in experimental parameters defining multi-agent environments and curiosity algorithms, then outputs training stability and performance data, allowing users to analyze the impact of curiosity on agent behavior. It's designed for AI researchers and machine learning engineers focusing on multi-agent reinforcement learning.
No commits in the last 6 months.
Use this if you are an AI researcher or machine learning engineer experimenting with multi-agent systems and want to evaluate the effectiveness of intrinsic reward mechanisms like curiosity for exploration, especially in environments with sparse rewards or partial observability.
Not ideal if you are looking for a plug-and-play solution for a business problem, or if you are not deeply involved in the research and development of reinforcement learning algorithms.
Stars
13
Forks
5
Language
Python
License
—
Category
Last pushed
Aug 16, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/LukasSchaefer/MSc_Curiosity_MARL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
gtri/scrimmage
Multi-Agent Robotics Simulator