HumanoidPPO.yaml

params:
  seed: ${...seed}

  algo:
    name: a2c_continuous

  model:
    name: continuous_a2c_logstd

  network:
    name: actor_critic
    separate: False

    space:
      continuous:
        mu_activation: None
        sigma_activation: None
        mu_init:
          name: glorot_uniform_initializer
          gain: 0.02
        sigma_init:
          name: const_initializer
          val: 0
        fixed_sigma: True

    mlp:
      units: [400, 200, 100]
      activation: swish
      d2rl: False
      initializer:
        name: default
  load_checkpoint: ${if:${...checkpoint},True,False} # flag which sets whether to load the checkpoint
  load_path: ${...checkpoint} # path to the checkpoint to load

  config:
    name: ${resolve_default:Humanoid,${....experiment}}
    full_experiment_name: ${.name}
    env_name: rlgpu
    multi_gpu: False
    mixed_precision: False
    normalize_input: True
    normalize_value: True
    value_bootstrap: True
    num_actors: ${....task.env.numEnvs}
    reward_shaper:
      scale_value: 1
    normalize_advantage: True
    gamma: 0.99
    tau: 0.95
    learning_rate: 5e-4
    lr_schedule: adaptive
    kl_threshold: 0.008
    score_to_win: 20000
    max_epochs: ${resolve_default:1000,${....max_iterations}}
    save_best_after: 200
    save_frequency: 100
    print_stats: True
    grad_norm: 1.0
    entropy_coef: 0.0
    truncate_grads: True
    ppo: True
    e_clip: 0.2
    horizon_length: 32
    minibatch_size: 32768
    mini_epochs: 5
    critic_coef: 1
    clip_value: False
    seq_len: 32
    bound_loss_type: 'regularisation' #'bound'
    bounds_loss_coef: 0.0005
    use_diagnostics: True