cartpole_ppo.yaml

alg_para:
  alg_name: PPO
  alg_config:
    process_num: 1
    save_model: True  # default False
    save_interval: 100

env_para:
  env_name: GymEnv
  env_info:
    name: CartPole-v0
    vision: False

agent_para:
  agent_name: PPO
  agent_num : 1
  agent_config:
    max_steps: 200
    complete_step: 2000000
    complete_episode: 9000

model_para:
  actor:
    model_name: PpoMlp
    state_dim: [4]
    action_dim: 2
    input_dtype: float32
    model_config:
      BATCH_SIZE: 200
      CRITIC_LOSS_COEF: 1.0
      ENTROPY_LOSS: 0.01
      LR: 0.0003
      LOSS_CLIPPING: 0.2
      MAX_GRAD_NORM: 5.0
      NUM_SGD_ITER: 8
      SUMMARY: False
      VF_SHARE_LAYERS: False
      activation: tanh
      hidden_sizes: [64, 64]

env_num: 10
speedup: False

benchmark:
  log_interval_to_train: 20
  eval:
    # model_path: /YOUR/PATH/TO/EVAL/models
    gap: 100
    model_divided_freq: 1   # how many times to divided of each model
    episodes_per_eval: 1
    evaluator_num: 1
    max_step_per_episode: 4000