mirror of
https://github.com/wassname/ray.git
synced 2026-07-06 05:16:30 +08:00
Richard Liaw
33 lines
1.9 KiB
YAML
33 lines
1.9 KiB
YAML
## Adapted from `https://github.com/oxwhirl/pymarl_alpha`.
|
|
|
|
env: sc2
|
|
|
|
env_args:
|
|
map_name: "3m_3m" # SC2 map name
|
|
difficulty: "7" # Very hard
|
|
move_amount: 2 # How much units are ordered to move per step
|
|
step_mul: 8 # How many frames are skiped per step
|
|
reward_sparse: False # Only +1/-1 reward for win/defeat (the rest of reward configs are ignored if True)
|
|
reward_only_positive: True # Reward is always positive
|
|
reward_negative_scale: 0.5 # How much to scale negative rewards, ignored if reward_only_positive=True
|
|
reward_death_value: 10 # Reward for killing an enemy unit and penalty for having an allied unit killed (if reward_only_poitive=False)
|
|
reward_scale: True # Whether or not to scale rewards before returning to agents
|
|
reward_scale_rate: 20 # If reward_scale=True, the agents receive the reward of (max_reward / reward_scale_rate), where max_reward is the maximum possible reward per episode
|
|
reward_win: 200 # Reward for win
|
|
reward_defeat: 0 # Reward for defeat (should be nonpositive)
|
|
state_last_action: True # Whether the last actions of units is a part of the state
|
|
obs_instead_of_state: False # Use combination of all agnets' observations as state
|
|
obs_own_health: True # Whether agents receive their own health as a part of observation
|
|
obs_all_health: True # Whether agents receive the health of all units (in the sight range) as a part of observataion
|
|
continuing_episode: False # Stop/continue episode after its termination
|
|
game_version: "4.1.2" # Ignored for Mac/Windows
|
|
save_replay_prefix: "" # Prefix of the replay to be saved
|
|
heuristic: False # Whether or not use a simple nonlearning hearistic as a controller
|
|
|
|
test_nepisode: 32
|
|
test_interval: 10000
|
|
log_interval: 2000
|
|
runner_log_interval: 2000
|
|
learner_log_interval: 2000
|
|
t_max: 2000000
|