Battle
This environment is part of the magent environments. Please read that page first for general information.
| Import | from pettingzoo.magent import battle_v3 |
| Actions | Discrete |
| Parallel API | Yes |
| Manual Control | No |
| Agents | agents= [red_[0-80], blue_[0-80]] |
| Agents | 162 |
| Action Shape | (21) |
| Action Values | Discrete(21) |
| Observation Shape | (13,13,5) |
| Observation Values | [0,2] |
| State Shape | (45, 45, 5) |
| State Values | (0, 2) |
Agent Environment Cycle
Battle
A large-scale team battle. Agents are rewarded for their individual performance, and not for the performance of their neighbors, so coordination is difficult. Agents slowly regain HP over time, so it is best to kill an opposing agent quickly. Specifically, agents have 10 HP, are damaged 2 HP by each attack, and recover 0.1 HP every turn.
Like all MAgent environments, agents can either move or attack each turn. An attack against another agent on their own team will not be registered.
Arguments
battle_v3.env(map_size=45, minimap_mode=False, step_reward=-0.005,
dead_penalty=-0.1, attack_penalty=-0.1, attack_opponent_reward=0.2,
max_cycles=1000, extra_features=False)
map_size: Sets dimensions of the (square) map. Increasing the size increases the number of agents. Minimum size is 12.
minimap_mode: Turns on global minimap observations. These observations include your and your opponents piece densities binned over the 2d grid of the observation space. Also includes your agent_position, the absolute position on the map (rescaled from 0 to 1).
step_reward: reward after every step
dead_penalty: reward when killed
attack_penalty: reward when attacking anything
attack_opponent_reward: reward added for attacking an opponent
max_cycles: number of frames (a step for each agent) until game terminates
extra_features: Adds additional features to observation (see table). Default False
Action space
Key: move_N means N separate actions, one to move to each of the N nearest squares on the grid.
Action options: [do_nothing, move_12, attack_8]
Reward
Reward is given as:
- 5 reward for killing an opponent
- -0.005 reward every step (step_reward option)
- -0.1 reward for attacking (attack_penalty option)
- 0.2 reward for attacking an opponent (attack_opponent_reward option)
- -0.1 reward for dying (dead_penalty option)
If multiple options apply, rewards are added.
Observation space
The observation space is a 13x13 map with the below channels (in order):
| feature | number of channels |
|---|---|
| obstacle/off the map | 1 |
| my_team_presence | 1 |
| my_team_hp | 1 |
| my_team_minimap(minimap_mode=True) | 1 |
| other_team_presence | 1 |
| other_team_hp | 1 |
| other_team_minimap(minimap_mode=True) | 1 |
| binary_agent_id(extra_features=True) | 10 |
| one_hot_action(extra_features=True) | 21 |
| last_reward(extra_features=True) | 1 |
| agent_position(minimap_mode=True) | 2 |
State space
The observation space is a 45x45 map. It contains the following channels, which are (in order):
| feature | number of channels |
|---|---|
| obstacle map | 1 |
| team_0_presence | 1 |
| team_0_hp | 1 |
| team_1_presence | 1 |
| team_1_hp | 1 |
| binary_agent_id(extra_features=True) | 10 |
| one_hot_action(extra_features=True) | 21 |
| last_reward(extra_features=True) | 1 |
Version History
- v3: Fixed bugs and changed default parameters (1.7.0)
- v2: Observation space bound fix, bumped version of all environments due to adoption of new agent iteration scheme where all agents are iterated over after they are done (1.4.0)
- v1: Agent order under death changed (1.3.0)
- v0: Initial versions release (1.0.0)