{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9629554152488708, "min": 0.9629554152488708, "max": 2.864976644515991, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9183.7060546875, "min": 9183.7060546875, "max": 29340.2265625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.850515365600586, "min": 0.30095231533050537, "max": 12.850515365600586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.8505859375, "min": 58.38475036621094, "max": 2589.59423828125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06558575345993364, "min": 0.06081037853374238, "max": 0.07681999448287374, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2623430138397346, "min": 0.2496208525981809, "max": 0.37701617971669843, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20636338769805196, "min": 0.12913214694708586, "max": 0.2667624161523931, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8254535507922078, "min": 0.5165285877883434, "max": 1.3261221400188172, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.4318181818181817, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 151.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.4318181818181817, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 151.0, "max": 1379.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689680774", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/drive/MyDrive/Colab Notebooks/ml_rl/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689681254" }, "total": 480.79191021099996, "count": 1, "self": 0.4335163680000278, "children": { "run_training.setup": { "total": 0.04557255600002463, "count": 1, "self": 0.04557255600002463 }, "TrainerController.start_learning": { "total": 480.3128212869999, "count": 1, "self": 0.5807785899837654, "children": { "TrainerController._reset_env": { "total": 4.193602706000092, "count": 1, "self": 4.193602706000092 }, "TrainerController.advance": { "total": 475.38115102601614, "count": 18200, "self": 0.28062391701996603, "children": { "env_step": { "total": 475.1005271089962, "count": 18200, "self": 349.5125304670189, "children": { "SubprocessEnvManager._take_step": { "total": 125.30835205498511, "count": 18200, "self": 1.8464436549838865, "children": { "TorchPolicy.evaluate": { "total": 123.46190840000122, "count": 18200, "self": 123.46190840000122 } } }, "workers": { "total": 0.27964458699216266, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 478.6512711739956, "count": 18200, "is_parallel": true, "self": 226.26686253399453, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005318990999967355, "count": 1, "is_parallel": true, "self": 0.003832147999901281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014868430000660737, "count": 10, "is_parallel": true, "self": 0.0014868430000660737 } } }, "UnityEnvironment.step": { "total": 0.04314717300007942, "count": 1, "is_parallel": true, "self": 0.0005901689999063819, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032195800008594233, "count": 1, "is_parallel": true, "self": 0.00032195800008594233 }, "communicator.exchange": { "total": 0.04018822800003363, "count": 1, "is_parallel": true, "self": 0.04018822800003363 }, "steps_from_proto": { "total": 0.002046818000053463, "count": 1, "is_parallel": true, "self": 0.00047875400059638196, "children": { "_process_rank_one_or_two_observation": { "total": 0.001568063999457081, "count": 10, "is_parallel": true, "self": 0.001568063999457081 } } } } } } }, "UnityEnvironment.step": { "total": 252.38440864000108, "count": 18199, "is_parallel": true, "self": 10.517189592989098, "children": { "UnityEnvironment._generate_step_input": { "total": 5.20512614900008, "count": 18199, "is_parallel": true, "self": 5.20512614900008 }, "communicator.exchange": { "total": 200.89980258999526, "count": 18199, "is_parallel": true, "self": 200.89980258999526 }, "steps_from_proto": { "total": 35.762290308016645, "count": 18199, "is_parallel": true, "self": 6.501669680976875, "children": { "_process_rank_one_or_two_observation": { "total": 29.26062062703977, "count": 181990, "is_parallel": true, "self": 29.26062062703977 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017381799989379942, "count": 1, "self": 0.00017381799989379942, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.72279015100867, "count": 454780, "is_parallel": true, "self": 10.027195607011663, "children": { "process_trajectory": { "total": 256.0065695189976, "count": 454780, "is_parallel": true, "self": 254.17113683499747, "children": { "RLTrainer._checkpoint": { "total": 1.835432684000125, "count": 4, "is_parallel": true, "self": 1.835432684000125 } } }, "_update_policy": { "total": 205.6890250249994, "count": 90, "is_parallel": true, "self": 81.78075429599357, "children": { "TorchPPOOptimizer.update": { "total": 123.90827072900584, "count": 4584, "is_parallel": true, "self": 123.90827072900584 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15711514700001317, "count": 1, "self": 0.0008543999999801599, "children": { "RLTrainer._checkpoint": { "total": 0.156260747000033, "count": 1, "self": 0.156260747000033 } } } } } } }