{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.8527554273605347, "min": 1.8527554273605347, "max": 2.8140251636505127, "count": 9 }, "SnowballTarget.Policy.Entropy.sum": { "value": 18831.40625, "min": 18831.40625, "max": 28756.5234375, "count": 9 }, "SnowballTarget.Step.mean": { "value": 99936.0, "min": 19968.0, "max": 99936.0, "count": 9 }, "SnowballTarget.Step.sum": { "value": 99936.0, "min": 19968.0, "max": 99936.0, "count": 9 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 7.591027736663818, "min": 1.1086370944976807, "max": 7.591027736663818, "count": 9 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1472.659423828125, "min": 211.74969482421875, "max": 1472.659423828125, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06284199073550054, "min": 0.06284199073550054, "max": 0.07222230205068128, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25136796294200214, "min": 0.25136796294200214, "max": 0.3611115102534064, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26206522405731913, "min": 0.18242232836143787, "max": 0.27795734469797095, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0482608962292765, "min": 0.7296893134457515, "max": 1.3897867234898549, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.5540094819999997e-05, "min": 1.5540094819999997e-05, "max": 0.00025314001562, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.216037927999999e-05, "min": 6.216037927999999e-05, "max": 0.0011172001275999998, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10518000000000001, "min": 0.10518000000000001, "max": 0.18438000000000002, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.42072000000000004, "min": 0.42072000000000004, "max": 0.8724, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00026848199999999995, "min": 0.00026848199999999995, "max": 0.004220562000000001, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0010739279999999998, "min": 0.0010739279999999998, "max": 0.018632759999999998, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 16.5, "min": 4.795454545454546, "max": 16.5, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 726.0, "min": 211.0, "max": 878.0, "count": 9 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 16.5, "min": 4.795454545454546, "max": 16.5, "count": 9 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 726.0, "min": 211.0, "max": 878.0, "count": 9 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704445237", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704445449" }, "total": 212.90651439500004, "count": 1, "self": 0.4380315000000792, "children": { "run_training.setup": { "total": 0.05446932199993171, "count": 1, "self": 0.05446932199993171 }, "TrainerController.start_learning": { "total": 212.41401357300003, "count": 1, "self": 0.29725998599644754, "children": { "TrainerController._reset_env": { "total": 1.8716924619999418, "count": 1, "self": 1.8716924619999418 }, "TrainerController.advance": { "total": 210.15313940000362, "count": 8202, "self": 0.1263093730087803, "children": { "env_step": { "total": 210.02683002699484, "count": 8202, "self": 138.40515514498225, "children": { "SubprocessEnvManager._take_step": { "total": 71.4880824670048, "count": 8202, "self": 0.6950981299992236, "children": { "TorchPolicy.evaluate": { "total": 70.79298433700558, "count": 8202, "self": 70.79298433700558 } } }, "workers": { "total": 0.13359241500779717, "count": 8202, "self": 0.0, "children": { "worker_root": { "total": 211.8185724749992, "count": 8202, "is_parallel": true, "self": 104.90280012300173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019655609999063017, "count": 1, "is_parallel": true, "self": 0.0005625499995858263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014030110003204754, "count": 10, "is_parallel": true, "self": 0.0014030110003204754 } } }, "UnityEnvironment.step": { "total": 0.037417448999917724, "count": 1, "is_parallel": true, "self": 0.0006318959998452556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003912250000439599, "count": 1, "is_parallel": true, "self": 0.0003912250000439599 }, "communicator.exchange": { "total": 0.034376875000020846, "count": 1, "is_parallel": true, "self": 0.034376875000020846 }, "steps_from_proto": { "total": 0.002017453000007663, "count": 1, "is_parallel": true, "self": 0.0003886959998453676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016287570001622953, "count": 10, "is_parallel": true, "self": 0.0016287570001622953 } } } } } } }, "UnityEnvironment.step": { "total": 106.91577235199748, "count": 8201, "is_parallel": true, "self": 4.986603081994986, "children": { "UnityEnvironment._generate_step_input": { "total": 2.566246203999526, "count": 8201, "is_parallel": true, "self": 2.566246203999526 }, "communicator.exchange": { "total": 83.20323664700811, "count": 8201, "is_parallel": true, "self": 83.20323664700811 }, "steps_from_proto": { "total": 16.159686418994852, "count": 8201, "is_parallel": true, "self": 3.009303545009857, "children": { "_process_rank_one_or_two_observation": { "total": 13.150382873984995, "count": 82010, "is_parallel": true, "self": 13.150382873984995 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003014119999988907, "count": 1, "self": 0.0003014119999988907, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 207.43462478898982, "count": 315782, "is_parallel": true, "self": 6.784712976016294, "children": { "process_trajectory": { "total": 115.88779060297293, "count": 315782, "is_parallel": true, "self": 115.52272035497288, "children": { "RLTrainer._checkpoint": { "total": 0.36507024800005183, "count": 2, "is_parallel": true, "self": 0.36507024800005183 } } }, "_update_policy": { "total": 84.7621212100006, "count": 40, "is_parallel": true, "self": 27.692921618999662, "children": { "TorchPPOOptimizer.update": { "total": 57.06919959100094, "count": 2037, "is_parallel": true, "self": 57.06919959100094 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09162031300002127, "count": 1, "self": 0.0016305279999642153, "children": { "RLTrainer._checkpoint": { "total": 0.08998978500005705, "count": 1, "self": 0.08998978500005705 } } } } } } }