[game]
module = "retro.examples.snake"

[metadata]
actions = [
    "KEY_RIGHT",
    "KEY_UP",
    "KEY_LEFT",
    "KEY_DOWN",
]
reward = "reward"
extras_size = 2
board_size = [
    17,
    17,
]
character_set = [
    "@",
    "*",
    ">",
    "<",
    "^",
    "v",
]
observation_function = "snake_observation:egocentric_observation"

[preprocessing]
spatial = false
board = true
observe_state = []

[model]
hidden_sizes = [
    128,
    64,
]

[training]
learning_rate = 0.0001
learning_rate_decay = 0.9999
gamma = 0.99
epsilon = 1.0
epsilon_decay = 0.9997
epsilon_min = 0.05
batch_size = 64
memory_capacity = 50000
target_update_freq = 500
train_every = 4
training_episodes = 20000
prioritize_experiences = true
exploration_turns = 200
unknown_character_strategy = "ignore"
max_turns_per_episode = 2000