Co-op Health Gathering

Tethered players survive in a toxic maze that damages them continuously. Health kits are scarce, so the team has to explore, collect and manage chain slack together.

import comrad

env = comrad.parallel_env("coop_health_gathering")

Gymnasium id	comrad/coop_health_gathering-v0
Agents	2 by default (supports 2–8)
Capability tested	Resource sharing under continuous damage
Episode limit	2100 steps
Observation	RGB image (72, 128, 3) per agent; measurement vector not available
Action space	Tuple(Discrete(3), Discrete(3), Discrete(3))
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. move: none / forward / backward
2. strafe: none / right / left
3. turn: none / left / right

Reward

Bonuses for health gained and kits picked up; penalties for health lost, death and stretching the chain.

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

Variants

• None.