general_cfg:
  algo_name: QLearning
  collect_traj: false
  device: cpu
  env_name: gym
  load_checkpoint: false
  load_model_step: best
  load_path: Train_single_CartPole-v1_DQN_20230515-211721
  max_episode: 300
  max_step: 100
  mode: train
  model_save_fre: 500
  mp_backend: single
  n_learners: 1
  n_workers: 1
  online_eval: false
  online_eval_episode: 10
  seed: 1
  share_buffer: true
algo_cfg:
  epsilon_decay: 300
  epsilon_end: 0.01
  epsilon_start: 0.95
  gamma: 0.99
  lr: 0.1
env_cfg:
  id: CliffWalking-v0
  ignore_params:
  - wrapper
  - ignore_params
  render_mode: null
  wrapper: null