{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6550472974777222, "min": 1.6550472974777222, "max": 2.856945037841797, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16894.72265625, "min": 16486.537109375, "max": 29320.826171875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.16292953491211, "min": 0.3482355773448944, "max": 9.16292953491211, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1869.2376708984375, "min": 67.55770111083984, "max": 1869.2376708984375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07037000068241969, "min": 0.06126856921507758, "max": 0.07437954536055937, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35185000341209843, "min": 0.24507427686031033, "max": 0.35185000341209843, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2372448506892896, "min": 0.17486804560986438, "max": 0.2636776950721647, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.186224253446448, "min": 0.6994721824394575, "max": 1.2565156297356477, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00027440009451199995, "min": 0.00027440009451199995, "max": 0.004729400005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0013720004725599998, "min": 0.0013720004725599998, "max": 0.02117200007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.69090909090909, "min": 2.9545454545454546, "max": 19.69090909090909, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1083.0, "min": 130.0, "max": 1083.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.69090909090909, "min": 2.9545454545454546, "max": 19.69090909090909, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1083.0, "min": 130.0, "max": 1083.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717186618", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717186974" }, "total": 356.0612305249999, "count": 1, "self": 0.5948508750000201, "children": { "run_training.setup": { "total": 0.1112556709999808, "count": 1, "self": 0.1112556709999808 }, "TrainerController.start_learning": { "total": 355.3551239789999, "count": 1, "self": 0.5846271469893054, "children": { "TrainerController._reset_env": { "total": 3.7871027640001103, "count": 1, "self": 3.7871027640001103 }, "TrainerController.advance": { "total": 350.8835018260104, "count": 9135, "self": 0.26525037100373083, "children": { "env_step": { "total": 350.61825145500666, "count": 9135, "self": 267.7970364420064, "children": { "SubprocessEnvManager._take_step": { "total": 82.55653434499595, "count": 9135, "self": 1.6457394019978437, "children": { "TorchPolicy.evaluate": { "total": 80.91079494299811, "count": 9135, "self": 80.91079494299811 } } }, "workers": { "total": 0.2646806680043028, "count": 9135, "self": 0.0, "children": { "worker_root": { "total": 354.0849314050056, "count": 9135, "is_parallel": true, "self": 169.12195152500726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003826389999858293, "count": 1, "is_parallel": true, "self": 0.0009254590004275087, "children": { "_process_rank_one_or_two_observation": { "total": 0.002900930999430784, "count": 10, "is_parallel": true, "self": 0.002900930999430784 } } }, "UnityEnvironment.step": { "total": 0.05640318200016736, "count": 1, "is_parallel": true, "self": 0.001118759000519276, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005493629998909455, "count": 1, "is_parallel": true, "self": 0.0005493629998909455 }, "communicator.exchange": { "total": 0.05197613899986209, "count": 1, "is_parallel": true, "self": 0.05197613899986209 }, "steps_from_proto": { "total": 0.0027589209998950537, "count": 1, "is_parallel": true, "self": 0.0005764130000898149, "children": { "_process_rank_one_or_two_observation": { "total": 0.002182507999805239, "count": 10, "is_parallel": true, "self": 0.002182507999805239 } } } } } } }, "UnityEnvironment.step": { "total": 184.96297987999833, "count": 9134, "is_parallel": true, "self": 8.825369824971403, "children": { "UnityEnvironment._generate_step_input": { "total": 4.404201518008676, "count": 9134, "is_parallel": true, "self": 4.404201518008676 }, "communicator.exchange": { "total": 147.01039572201194, "count": 9134, "is_parallel": true, "self": 147.01039572201194 }, "steps_from_proto": { "total": 24.723012815006314, "count": 9134, "is_parallel": true, "self": 5.067369048961609, "children": { "_process_rank_one_or_two_observation": { "total": 19.655643766044705, "count": 91340, "is_parallel": true, "self": 19.655643766044705 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0007086890000209678, "count": 1, "self": 0.0007086890000209678, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 346.652125065978, "count": 440241, "is_parallel": true, "self": 11.077732069043122, "children": { "process_trajectory": { "total": 192.25149183093595, "count": 440241, "is_parallel": true, "self": 191.90913960993612, "children": { "RLTrainer._checkpoint": { "total": 0.3423522209998282, "count": 2, "is_parallel": true, "self": 0.3423522209998282 } } }, "_update_policy": { "total": 143.32290116599893, "count": 45, "is_parallel": true, "self": 39.24553519200094, "children": { "TorchPPOOptimizer.update": { "total": 104.07736597399798, "count": 2292, "is_parallel": true, "self": 104.07736597399798 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09918355300010262, "count": 1, "self": 0.0014053019999664684, "children": { "RLTrainer._checkpoint": { "total": 0.09777825100013615, "count": 1, "self": 0.09777825100013615 } } } } } } }