Ryukijano
/

marl-world-model

marl-ippo-actor-critic

multi-agent-reinforcement-learning

warehouse-robotics

Model card Files Files and versions

marl-world-model

75.2 MB

Ctrl+K

Ctrl+K

2 contributors

History: 4 commits

Devin

Add README.md and config.json with architecture/metadata

f4ec55f about 17 hours ago

checkpoints
Add trained IPPO checkpoints about 17 hours ago
outputs
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
.gitattributes
1.52 kB
initial commit about 17 hours ago
AGENTS.md
9.29 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
DESIGN.md
2.82 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
README.md
9.32 kB
Add README.md and config.json with architecture/metadata about 17 hours ago
config.json
2.93 kB
Add README.md and config.json with architecture/metadata about 17 hours ago
convert_to_lerobot.py
21.7 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
env_multi_agent_isaac.py
43.6 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
marl_ippo.py
30 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
run_marl.py
28.8 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
so101_bridge.py
32.5 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago
world_model.py
55.3 kB
MARL + world model source code and design docs (2026-08-13 03:14:28) about 17 hours ago