{
  "ppo": {
    "best_objective": -10.562240600585938,
    "best_params": {
      "clip_epsilon": 0.1937704475953032,
      "entropy_coeff": 0.004575857121380468,
      "policy_learning_rate": 0.0009063277596553022,
      "value_learning_rate": 0.00008412342994353697,
      "value_loss_coeff": 1.3082900521181515
    },
    "elapsed_secs": 4.173037206,
    "trials": 6
  }
}