# can expect improvement to -140 reward in ~300-500k timesteps
pendulum-ppo:
    env: Pendulum-v0
    run: PPO
    config:
        train_batch_size: 2048
        vf_clip_param: 10.0
        num_workers: 0
        num_envs_per_worker: 10
        lambda: 0.1
        gamma: 0.95
        lr: 0.0003
        sgd_minibatch_size: 64
        num_sgd_iter: 10
        model:
            fcnet_hiddens: [64, 64]
        batch_mode: complete_episodes
        observation_filter: MeanStdFilter