ppo.json

{
  "agent": "ppo",
  "network": {
    "type": "auto",
    "rnn": false
  },
  "use_beta_distribution": false,
  "memory": "minimum",
  "batch_size": 128,
  "update_frequency": 1,
  "learning_rate": 0.01,
  "multi_step": 5,
  "subsampling_fraction": 0.9131375430837279,
  "likelihood_ratio_clipping": 0.09955676846552193,
  "discount": 0.9985351346308641,
  "predict_terminal_values": false,
  "baseline": {
    "type": "auto",
    "rnn": false
  },
  "baseline_optimizer": {
    "optimizer": "adam",
    "learning_rate": 0.01,
    "multi_step": 10
  },
  "state_preprocessing": "linear_normalization",
  "reward_preprocessing": null,
  "exploration": 0.0,
  "variable_noise": 0.0,
  "l2_regularization": 0.0,
  "entropy_regularization": 0.0011393096635237982,
  "summarizer": {
    "directory": "./Graph",
    "summaries": [
      "loss",
      "reward"
    ]
  }
}