default_settings: null
behaviors:
  TauAgent:
    trainer_type: ppo
    hyperparameters:
      batch_size: 256
      buffer_size: 4096
      learning_rate: 3.0e-05
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 5
      shared_critic: false
      learning_rate_schedule: linear
      beta_schedule: linear
      epsilon_schedule: linear
    checkpoint_interval: 250000
    network_settings:
      normalize: true
      hidden_units: 256
      num_layers: 4
      vis_encode_type: simple
      memory:
        sequence_length: 256
        memory_size: 256
      goal_conditioning_type: hyper
      deterministic: false
    reward_signals:
      extrinsic:
        gamma: 0.99
        strength: 1.0
        network_settings:
          normalize: false
          hidden_units: 128
          num_layers: 2
          vis_encode_type: simple
          memory: null
          goal_conditioning_type: hyper
          deterministic: false
      curiosity:
        gamma: 0.995
        strength: 0.1
        network_settings:
          normalize: true
          hidden_units: 256
          num_layers: 4
          vis_encode_type: simple
          memory: null
          goal_conditioning_type: hyper
          deterministic: false
        learning_rate: 0.0003
        encoding_size: null
    init_path: results\tau_agent_B1\TauAgent\checkpoint.pt
    keep_checkpoints: 40
    even_checkpoints: false
    max_steps: 10000000
    time_horizon: 256
    summary_freq: 10000
    threaded: true
    self_play: null
    behavioral_cloning: null
env_settings:
  env_path: .\Build
  env_args: null
  base_port: 5005
  num_envs: 1
  num_areas: 1
  timeout_wait: 300
  seed: -1
  max_lifetime_restarts: 10
  restarts_rate_limit_n: 1
  restarts_rate_limit_period_s: 60
engine_settings:
  width: 84
  height: 84
  quality_level: 5
  time_scale: 20
  target_frame_rate: -1
  capture_frame_rate: 60
  no_graphics: false
environment_parameters: null
checkpoint_settings:
  run_id: tau_agent_B2
  initialize_from: tau_agent_B1
  load_model: false
  resume: false
  force: true
  train_model: false
  inference: false
  results_dir: results
torch_settings:
  device: cuda
debug: false