KR
Activity
Challenge Categories
Challenges Entered
Completed
Sony Group Corporation
Generate Synchronised & Contextually Accurate Videos
Latest submissions
AIcrowd
Cooperative AI Foundation
Multi-Agent Dynamics & Mixed-Motive Cooperation
Latest submissions
See All| graded | 239455 | ||
| graded | 239045 | ||
| failed | 239043 |
Learn Prompting
Towards AI
Preamble
Trick Large Language Models
Latest submissions
ASCII-rendered single-player dungeon crawl game
Latest submissions
MineRL Labs - Carnegie Mellon University
Training sample-efficient agents in Minecraft
Latest submissions
Self-driving RL on DeepRacer cars - From simulation to real world
Latest submissions
See All| graded | 157325 |
Spotify
A dataset and open-ended challenge for music recommendation research
Latest submissions
Seerave Foundation
A benchmark for image-based food recognition
Latest submissions
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Dr Derk
Multi-agent RL in game environment. Train your Derklings, creatures with a neural network brain, to fight for you!
Latest submissions
See All| graded | 116469 | ||
| graded | 114915 | ||
| failed | 114722 |
Stanford Neuromuscular Biomechanics Laboratory
Reinforcement Learning on Musculoskeletal Models
Latest submissions
Sample-efficient reinforcement learning in Minecraft
Latest submissions
See All| graded | 18964 | ||
| graded | 18959 | ||
| graded | 18926 |
Computer Vision Lab - ETH Zurich
Immitation Learning for Autonomous Driving
Latest submissions
EPFL ML
Predict Heart Disease
Latest submissions
| Participant | Rating |
|---|
| Participant | Rating |
|---|
Dr. Derks Mutant Battlegrounds
Derk3: Open submission and potential baseline
Almost 5 years agoThank you very much. I really need a baseline code 
Dr Derk Mutant Battleground | Research Paper and Resources 📚
Almost 5 years agoThank you very much. It will be really useful for making RL agent 
Rewards for Successful Submission | Dr Derk Steam Keys 🎮
Almost 5 years agoThank you! It is good news.
Derk3: Open submission and potential baseline
Almost 5 years agoI ran your code. Training goes well
In my case, I am training my agent using ‘IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures’ of DeepMind.
Thank you for your baseline code. I want to share my code soon after getting an appropriate performance.