{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9225225448608398, "min": 0.9219985604286194, "max": 2.8666319847106934, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8808.2451171875, "min": 8808.2451171875, "max": 29388.7109375, "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": 12.673772811889648, "min": 0.4670991897583008, "max": 12.673772811889648, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2471.3857421875, "min": 90.61724090576172, "max": 2530.05615234375, "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": 0.07317694450167063, "min": 0.06298318489080332, "max": 0.07596798663144, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2927077780066825, "min": 0.2701700294216839, "max": 0.3706483812637481, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18034308045810343, "min": 0.14044661062778724, "max": 0.27492330705418305, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7213723218324137, "min": 0.561786442511149, "max": 1.3411314002439088, "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": 3.6818181818181817, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 162.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.6818181818181817, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 162.0, "max": 1391.0, "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": "1682301007", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnoballTarget.yml --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": "1682301477" }, "total": 470.56465209099997, "count": 1, "self": 0.4400919199999862, "children": { "run_training.setup": { "total": 0.12141013899997688, "count": 1, "self": 0.12141013899997688 }, "TrainerController.start_learning": { "total": 470.003150032, "count": 1, "self": 0.5953499320046944, "children": { "TrainerController._reset_env": { "total": 3.912209254000004, "count": 1, "self": 3.912209254000004 }, "TrainerController.advance": { "total": 465.35638612599547, "count": 18202, "self": 0.2756336719964452, "children": { "env_step": { "total": 465.080752453999, "count": 18202, "self": 340.44327466700605, "children": { "SubprocessEnvManager._take_step": { "total": 124.36314534799163, "count": 18202, "self": 1.6894787209845958, "children": { "TorchPolicy.evaluate": { "total": 122.67366662700704, "count": 18202, "self": 122.67366662700704 } } }, "workers": { "total": 0.2743324390013413, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 468.36665312200296, "count": 18202, "is_parallel": true, "self": 214.33061501200507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005521295999983522, "count": 1, "is_parallel": true, "self": 0.004021961000091778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014993349998917438, "count": 10, "is_parallel": true, "self": 0.0014993349998917438 } } }, "UnityEnvironment.step": { "total": 0.043816875999993954, "count": 1, "is_parallel": true, "self": 0.0006058810000126869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042796899998620574, "count": 1, "is_parallel": true, "self": 0.00042796899998620574 }, "communicator.exchange": { "total": 0.040781288000005134, "count": 1, "is_parallel": true, "self": 0.040781288000005134 }, "steps_from_proto": { "total": 0.0020017379999899276, "count": 1, "is_parallel": true, "self": 0.0003967919999467995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016049460000431282, "count": 10, "is_parallel": true, "self": 0.0016049460000431282 } } } } } } }, "UnityEnvironment.step": { "total": 254.0360381099979, "count": 18201, "is_parallel": true, "self": 10.241910083995492, "children": { "UnityEnvironment._generate_step_input": { "total": 5.508312382002828, "count": 18201, "is_parallel": true, "self": 5.508312382002828 }, "communicator.exchange": { "total": 204.1778509620023, "count": 18201, "is_parallel": true, "self": 204.1778509620023 }, "steps_from_proto": { "total": 34.10796468199726, "count": 18201, "is_parallel": true, "self": 6.511090649019479, "children": { "_process_rank_one_or_two_observation": { "total": 27.59687403297778, "count": 182010, "is_parallel": true, "self": 27.59687403297778 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017843799992078857, "count": 1, "self": 0.00017843799992078857, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.7741393979709, "count": 420572, "is_parallel": true, "self": 10.549976889967581, "children": { "process_trajectory": { "total": 258.1932992050035, "count": 420572, "is_parallel": true, "self": 256.8642443200035, "children": { "RLTrainer._checkpoint": { "total": 1.329054885000005, "count": 4, "is_parallel": true, "self": 1.329054885000005 } } }, "_update_policy": { "total": 193.03086330299982, "count": 90, "is_parallel": true, "self": 68.95856617099696, "children": { "TorchPPOOptimizer.update": { "total": 124.07229713200286, "count": 4587, "is_parallel": true, "self": 124.07229713200286 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13902628199991796, "count": 1, "self": 0.0009110190000001239, "children": { "RLTrainer._checkpoint": { "total": 0.13811526299991783, "count": 1, "self": 0.13811526299991783 } } } } } } }