general_cfg:
  algo_name: CQL
  device: cpu
  env_name: CartPole-v1
  eval_eps: 10
  eval_per_episode: 5
  load_checkpoint: false
  load_path: tasks
  max_steps: 200
  mode: train
  new_step_api: true
  render: false
  save_fig: true
  seed: 1
  show_fig: true
  test_eps: 20
  train_eps: 300
  wrapper: null
algo_cfg:
  batch_size: 64
  buffer_size: 100000
  epsilon_decay: 500
  epsilon_end: 0.01
  epsilon_start: 0.95
  gamma: 0.99
  lr: 0.001
  target_update: 4
  tau: 0.001
  value_layers:
  - activation: relu
    layer_dim:
    - n_states
    - 256
    layer_type: linear
  - activation: relu
    layer_dim:
    - 256
    - 256
    layer_type: linear
  - activation: none
    layer_dim:
    - 256
    - n_actions
    layer_type: linear