Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/vmas-simulator-guide
Vectorized multi-agent reinforcement learning simulator
Passed 21 of 22 test cases with the skill, and 19 of 22 without it.
2 fixed19 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to instantiate 1024 parallel environments of the cooperative landmark coverage task on CUDA in VMAS. Standard gym.make uses strings like Gym 'SimpleSpread-v0'. How do I construct this in VMAS?
| Checked | Without skill | With skill |
|---|---|---|
| The response uses vmas.make_env | Passed | Passed |
| The response specifies scenario='simple_spread' | Missed | Passed |
| The response specifies device='cuda' | Passed | Passed |
The instructions your model reads when the skill loads.
VMAS is a vectorized simulator for multi-agent reinforcement learning (MARL) that runs thousands of parallel environments on GPU via PyTorch. It provides a diverse set of 2D cooperative, competitive, and mixed scenarios for benchmarking multi-agent algorithms. Orders of magnitude faster than CPU-based simulators, enabling rapid research iteration on multi-agent coordination problems.
pip install vmas
import vmas
# Create vectorized environment
env = vmas.make_env(
scenario="simple_spread",
num_envs=1024, # Parallel environments
num_agents=3,
device="cuda", # GPU acceleration
continuous_actions=True,
)
# Environment loop
obs = env.reset()
for step in range(100):
# Random actions for demonstration
actions = [env.action_space[i].sample()
for i in range(env.n_agents)]
obs, rewards, dones, infos = env.step(actions)
# obs: list of [num_envs, obs_dim] tensors
# rewards: list of [num_envs] tensors
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.