behaviors:
  WormDynamic:
    trainer_type: ppo
    hyperparameters:
      batch_size: 2024
      buffer_size: 20240
      learning_rate: 0.0003
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
      learning_rate_schedule: linear
    network_settings:
      normalize: true
      hidden_units: 512
      num_layers: 3
      vis_encode_type: simple
      memory: null
    reward_signals:
      extrinsic:
        gamma: 0.995
        strength: 1.0
    init_path: null
    keep_checkpoints: 5
    checkpoint_interval: 500000
    max_steps: 3500000
    time_horizon: 1000
    summary_freq: 30000
    threaded: true
    self_play: null
    behavioral_cloning: null
env_settings:
  env_path: null
  env_args: null
  base_port: 5005
  num_envs: 1
  seed: -1
engine_settings:
  width: 84
  height: 84
  quality_level: 5
  time_scale: 20
  target_frame_rate: -1
  capture_frame_rate: 60
  no_graphics: false
parameter_randomization: null
curriculum: null
checkpoint_settings:
  run_id: WormDynamic2
  initialize_from: null
  load_model: false
  resume: true
  force: false
  train_model: false
  inference: false
debug: false