general_cfg: algo_name: NoisyDQN device: cpu env_name: gym eval_eps: 10 eval_per_episode: 5 load_checkpoint: false load_path: Train_CartPole-v1_NoisyDQN max_steps: 200 mode: train mp_backend: ray n_workers: 2 new_step_api: true render: false render_mode: human save_fig: true seed: 1 show_fig: false test_eps: 10 train_eps: 220 wrapper: null algo_cfg: batch_size: 64 buffer_size: 100000 epsilon_decay: 500 epsilon_end: 0.01 epsilon_start: 0.95 gamma: 0.95 hidden_dim: 256 lr: 0.0001 target_update: 4 tau: 1.0 env_cfg: id: CartPole-v1 new_step_api: true render_mode: null