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.
Previously the game ran indefinitely and relied entirely on
max_turns_per_episode to end an episode. Add start/food energy values
so an episode ends on its own when energy runs out, and mention
retro-gamer plot in the lab's training log instructions.
