7788e34ebd
BabySnake's tabular Q-learning exercise needs a small discrete state, not the flattened board encoding retro_gamer normally produces. Define get_state(game) in babysnake_env.py, returning a plain (agent_x, agent_y, food_x, food_y) tuple, and point babysnake's observation_function at it instead of declaring a character_set. Disable the on-screen state overlay so it doesn't clutter the terminal watch view.
5 lines
144 B
TOML
5 lines
144 B
TOML
[tool.retro-gamer]
|
|
actions = ["KEY_RIGHT", "KEY_UP", "KEY_LEFT", "KEY_DOWN"]
|
|
reward = "reward"
|
|
observation_function = "babysnake_env:get_state"
|