# Pendulum SAC can attain -150+ reward in 6-7k
# Configurations are the similar to original softlearning/sac codebase
pendulum_sac:
    env: Pendulum-v0
    run: SAC
    stop:
        episode_reward_mean: -150
    config:
        horizon: 200
        soft_horizon: False
        Q_model:
          hidden_activation: relu
          hidden_layer_sizes: [256, 256]
        policy_model:
          hidden_activation: relu
          hidden_layer_sizes: [256, 256]
        tau: 0.005
        target_entropy: auto
        no_done_at_end: True
        n_step: 1
        sample_batch_size: 1
        prioritized_replay: False
        train_batch_size: 256
        target_network_update_freq: 1
        timesteps_per_iteration: 1000
        learning_starts: 256
        optimization:
          actor_learning_rate: 0.0003
          critic_learning_rate: 0.0003
          entropy_learning_rate: 0.0003
        num_workers: 0
        num_gpus: 0
        clip_actions: False
        normalize_actions: True
        evaluation_interval: 1
        metrics_smoothing_episodes: 5