ant-rand-goal-maml:
    env: ray.rllib.examples.env.ant_rand_goal.AntRandGoalEnv
    run: MAML
    stop:
        training_iteration: 1000
    config:
        horizon: 200
        rollout_fragment_length: 200
        num_envs_per_worker: 20
        inner_adaptation_steps: 2
        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: 32
        num_gpus: 1
        inner_lr: 0.03
        explore: True
        clip_actions: False
        model:
            fcnet_hiddens: [64, 64]
            free_log_std: True