Cognitive AI Systems
Popular repositories Loading
-
MAPF-GPT-DDG
MAPF-GPT-DDG Public[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delt…
-
learn-to-follow
learn-to-follow Public[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm f…
-
when-to-switch
when-to-switch Public"When to Switch" Implementation: Addressing the PO-MAPF challenge with RePlan & EPOM policies. This repo includes search-based re-planning, reinforcement learning techniques, and three mixed polici…
-
pogema-benchmark
pogema-benchmark PublicThis is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.
Repositories
- pogema-toolbox Public
Cognitive-AI-Systems/pogema-toolbox’s past year of commit activity - marl-gpt Public
[AAMAS-2026] MARL-GPT: This work tackles the challenge of a general-purpose model for multi-agent reinforcement learning. The proposed MARL-GPT uses offline RL on large-scale expert trajectories, leveraging a single GPT-based transformer encoder to train one model that performs competitively across diverse MARL environments (SMACv2, GRF and POGEMA)
Cognitive-AI-Systems/marl-gpt’s past year of commit activity - pogema Public
[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.
Cognitive-AI-Systems/pogema’s past year of commit activity - MAPF-GPT-DDG Public
[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.
Cognitive-AI-Systems/MAPF-GPT-DDG’s past year of commit activity - pogema-benchmark Public
This is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.
Cognitive-AI-Systems/pogema-benchmark’s past year of commit activity - him-agent Public
The Hierarchical Intrinsically Motivated Agent (HIMA) is an algorithm that is intended to exhibit an adaptive goal-directed behavior using neurophysiological models of the neocortex, basal ganglia, and thalamus.
Cognitive-AI-Systems/him-agent’s past year of commit activity - learn-to-follow Public
[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm for constructing a long-term plan and reinforcement learning for resolving local conflicts.
Cognitive-AI-Systems/learn-to-follow’s past year of commit activity - mats-lp Public
[AAAI-2024] MATS-LP addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed approach utilizes a combination of Monte Carlo Tree Search and reinforcement learning for resolving conflicts.
Cognitive-AI-Systems/mats-lp’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…