Ammo Carrier

Fixed asymmetric roles: an immobile defender holds the hub against enemies, and a runner keeps the defender supplied with ammunition from depots.

import comrad

env = comrad.parallel_env("ammo_carrier")

Gymnasium id	comrad/ammo_carrier-v0
Agents	2 by default (supports 2)
Capability tested	Role-specialised logistics, resupply timing
Episode limit	2100 steps
Observation	RGB image (72, 128, 3) per agent; measurement vector available with additional_input=True
Action space	Tuple(Discrete(3), Discrete(2), Discrete(3), Discrete(2))
Default shared_reward	0.0: each agent receives its own reward
Score (info["true_objective"])	Survival time (episode steps)

Actions

Each agent sends one choice per head; index 0 is always "do nothing".

1. turn: none / left / right
2. move: none / forward
3. strafe: none / left / right
4. attack: none / attack

Reward

Role-specific, per agent: the defender is rewarded for kills and damage, the runner for collecting and delivering ammo; penalties for death. Rewards are not shared by default.

The score in info["true_objective"] is what the benchmark reports. The shaped reward is only a training signal.

Variants

• None.