checkpoints/params/agent.yaml

params:
  seed: 42
  env:
    clip_observations: 5.0
    clip_actions: 1.0
  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: default
        sigma_init:
          name: const_initializer
          val: 0
        fixed_sigma: true
    mlp:
      units:
      - 512
      - 256
      - 128
      activation: elu
      d2rl: false
      initializer:
        name: default
      regularizer:
        name: None
  load_checkpoint: false
  load_path: ''
  config:
    name: Galaxea-LongTrajectoryAssembly-Direct-v0
    full_experiment_name: LongTrajectoryAssembly
    env_name: rlgpu
    device: cuda:0
    device_name: cuda:0
    multi_gpu: false
    ppo: true
    mixed_precision: false
    normalize_input: true
    normalize_value: true
    num_actors: -1
    reward_shaper:
      scale_value: 1.0
    normalize_advantage: true
    gamma: 0.99
    tau: 0.95
    learning_rate: 3e-4
    lr_schedule: adaptive
    kl_threshold: 0.008
    score_to_win: 100000
    max_epochs: 3000
    save_best_after: 100
    save_frequency: 100
    print_stats: true
    grad_norm: 1.0
    entropy_coef: 0.001
    truncate_grads: true
    e_clip: 0.2
    clip_value: true
    horizon_length: 32
    minibatch_size: 16384
    mini_epochs: 8
    critic_coef: 2
    bounds_loss_coef: 0.0001
    games_to_track: 100
    player:
      deterministic: true
      games_num: 1000000
      print_stats: true
    train_dir: /home/ubuntu/gearboxAssembly/logs/rl_games/Galaxea-LongTrajectoryAssembly-Direct-v0