# This configuration can expect to reach -160 reward in 10k-20k timesteps
pendulum-ddpg:
    env: Pendulum-v0
    run: TD3
    stop:
        episode_reward_mean: -130
        time_total_s: 900 # 10 minutes
    config:
        # === Model ===
        actor_hiddens: [64, 64]
        critic_hiddens: [64, 64]

        # === Exploration ===
        learning_starts: 5000
        pure_exploration_steps: 5000

        # === Evaluation ===
        evaluation_interval: 1
        evaluation_num_episodes: 5