halfcheetah-rand-direc-maml:
    env: ray.rllib.examples.env.halfcheetah_rand_direc.HalfCheetahRandDirecEnv
    run: MAML
    stop:
        training_iteration: 1000    
    config:
        horizon: 100
        rollout_fragment_length: 100
        num_envs_per_worker: 20
        inner_adaptation_steps: 1
        maml_optimizer_steps: 5
        gamma: 0.99
        lambda: 1.0
        lr: 0.001
        vf_loss_coeff: 0.5
        clip_param: 0.3
        kl_target: 0.01
        kl_coeff: 0.0005
        num_workers: 31
        num_gpus: 1
        inner_lr: 0.1
        clip_actions: False
        model:
            fcnet_hiddens: [64, 64]
            free_log_std: True