Alexey Skrynnik retweeted
What a way to wrap up @IgluContest!
Our paper “IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents” accepted to @SIGIRConf including:
1) rich multi-modal dataset
2) A data collection tool
3) An online eval framework
#SIGIR2025
I’m happy to share that our paper, POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding, has been accepted to the ICLR 2025 Conference!
arxiv.org/abs/2407.14931
openreview.net/forum?id=6Vgw…
See you in Singapore!
I’m happy to announce that our paper, MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale, has been accepted to the AAAI 2025 Conference!
arxiv.org/abs/2409.00134
github.com/CognitiveAISystem…
MAPF-GPT performs exceptionally well on unseen instances and outperforms state-of-the-art learnable solvers such as SCRIMP and DCC, having better runtime efficiency. (2/3)
Here are the links to the preprint: arxiv.org/abs/2409.00134 and the source code: github.com/Cognitive-AI-Syst…. The repository includes training code, pre-trained weights for the 2M, 6M, and 85M models (uploaded to HuggingFace), and a dataset of 1 billion observation/action pairs.
I’m excited to announce our recent preprint titled MAPF-GPT, a GPT-like model designed for MAPF problems. It is trained using pure imitation learning on trajectories generated by LaCAM. (1/3)
Alexey Skrynnik retweeted
PRL (Workshop) @ ICAPS 2024 *CALL* - If you're bridging the gap between AI Planning and Reinforcement Learning, join the PRL workshop - prl-theworkshop.github.io/pr…. Submissions due March 22
I'm excited to announce that two of my papers have been accepted at AAAI-2024, delving into lifelong multi-agent pathfinding (LMAPF) using RL and planning techniques. Here's the thread: (1/7).
Against centralized MAPF algorithms, Follower excels, especially under a strict 1-second time constraint in scenarios with a large number of agents (over 160 for the Warehouse map). (6/7)
More details: ar5iv.labs.arxiv.org/html/23…. Big thanks to my co-authors Anton Andreychuk, Maria Nesterova, Konstantin Yakovlev, and Aleksandr Panov.
The second paper, which I will detail after the camera-ready version, focuses on using Neural MCTS for the LMAPF tasks. (7/7)
I've spent 72,763 hours training 24,970 models on @wandb! My #longestrun, eager-cosmos-1, trained for 961 hours. Here's its collector card: wandb.ai/year-wrapped-july-2…
Alexey Skrynnik retweeted
Congratulations to @stockfishchess for reporting their 14th victory at @chessdom's TCEC after a close battle against @LeelaChessZero! Both the engines, like lichess, are run by a community of #freesoftware enthusiasts: yet another victory for #libre software in the chess world!
Alexey Skrynnik retweeted
Exciting news! @IgluContest is bringing online testing of #RL agents. We need your help to make it perfect! Join us and register to test our agents and play #Minecraft. Let's unleash the true potential of human-AI collaboration!
forms.gle/C45KEu6PPPGvcoYy7
youtu.be/PWrvLhQDybw
