{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40479576587677, "min": 1.40479576587677, "max": 1.4262832403182983, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70746.921875, "min": 68906.0859375, "max": 77985.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.35085007727976, "min": 74.21385542168674, "max": 386.5615384615385, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49399.0, "min": 49278.0, "max": 50253.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49991.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49991.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4954729080200195, "min": 0.10935484617948532, "max": 2.5171620845794678, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1614.571044921875, "min": 14.106775283813477, "max": 1650.9215087890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9151884355169178, "min": 1.7759710487931273, "max": 4.0382681907269, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2533.1269177794456, "min": 229.10026529431343, "max": 2586.368226826191, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9151884355169178, "min": 1.7759710487931273, "max": 4.0382681907269, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2533.1269177794456, "min": 229.10026529431343, "max": 2586.368226826191, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019103528304711088, "min": 0.014227674743203049, "max": 0.020454438457575937, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05731058491413326, "min": 0.028455349486406097, "max": 0.057827948908864835, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05863657374348905, "min": 0.02132847082490722, "max": 0.0604518906523784, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17590972123046716, "min": 0.04265694164981444, "max": 0.1813556719571352, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6815987728333375e-06, "min": 3.6815987728333375e-06, "max": 0.0002953593765468749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1044796318500013e-05, "min": 1.1044796318500013e-05, "max": 0.0008440443186519, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122716666666669, "min": 0.10122716666666669, "max": 0.19845312500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30368150000000005, "min": 0.2076262, "max": 0.5813480999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.123561666666675e-05, "min": 7.123561666666675e-05, "max": 0.004922810937499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021370685000000024, "min": 0.00021370685000000024, "max": 0.014069270190000002, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707226407", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707228817" }, "total": 2409.440081134, "count": 1, "self": 0.44169744000009814, "children": { "run_training.setup": { "total": 0.04923977999987983, "count": 1, "self": 0.04923977999987983 }, "TrainerController.start_learning": { "total": 2408.949143914, "count": 1, "self": 4.509431323028366, "children": { "TrainerController._reset_env": { "total": 2.9892884610001147, "count": 1, "self": 2.9892884610001147 }, "TrainerController.advance": { "total": 2401.323403468972, "count": 233222, "self": 4.9041543729199475, "children": { "env_step": { "total": 1939.5104788280173, "count": 233222, "self": 1609.9971716006812, "children": { "SubprocessEnvManager._take_step": { "total": 326.6790022380692, "count": 233222, "self": 16.749791363120494, "children": { "TorchPolicy.evaluate": { "total": 309.9292108749487, "count": 222963, "self": 309.9292108749487 } } }, "workers": { "total": 2.8343049892669114, "count": 233222, "self": 0.0, "children": { "worker_root": { "total": 2401.659049063007, "count": 233222, "is_parallel": true, "self": 1088.6713370230154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009009340001284727, "count": 1, "is_parallel": true, "self": 0.00025307400005658565, "children": { "_process_rank_one_or_two_observation": { "total": 0.000647860000071887, "count": 2, "is_parallel": true, "self": 0.000647860000071887 } } }, "UnityEnvironment.step": { "total": 0.032897016000106305, "count": 1, "is_parallel": true, "self": 0.00039493999975093175, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025312900015705964, "count": 1, "is_parallel": true, "self": 0.00025312900015705964 }, "communicator.exchange": { "total": 0.03144854800007124, "count": 1, "is_parallel": true, "self": 0.03144854800007124 }, "steps_from_proto": { "total": 0.0008003990001270722, "count": 1, "is_parallel": true, "self": 0.00020498000026236696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005954189998647053, "count": 2, "is_parallel": true, "self": 0.0005954189998647053 } } } } } } }, "UnityEnvironment.step": { "total": 1312.9877120399915, "count": 233221, "is_parallel": true, "self": 41.25639111639907, "children": { "UnityEnvironment._generate_step_input": { "total": 85.96511211693633, "count": 233221, "is_parallel": true, "self": 85.96511211693633 }, "communicator.exchange": { "total": 1092.4745247058486, "count": 233221, "is_parallel": true, "self": 1092.4745247058486 }, "steps_from_proto": { "total": 93.29168410080752, "count": 233221, "is_parallel": true, "self": 34.65772516784432, "children": { "_process_rank_one_or_two_observation": { "total": 58.633958932963196, "count": 466442, "is_parallel": true, "self": 58.633958932963196 } } } } } } } } } } }, "trainer_advance": { "total": 456.90877026803514, "count": 233222, "self": 6.625547788050881, "children": { "process_trajectory": { "total": 158.5469349989853, "count": 233222, "self": 157.33874496698422, "children": { "RLTrainer._checkpoint": { "total": 1.2081900320010845, "count": 10, "self": 1.2081900320010845 } } }, "_update_policy": { "total": 291.73628748099895, "count": 97, "self": 231.13104093599577, "children": { "TorchPPOOptimizer.update": { "total": 60.60524654500318, "count": 2910, "self": 60.60524654500318 } } } } } } }, "trainer_threads": { "total": 1.3639996723213699e-06, "count": 1, "self": 1.3639996723213699e-06 }, "TrainerController._save_models": { "total": 0.12701929700006076, "count": 1, "self": 0.002057402000446018, "children": { "RLTrainer._checkpoint": { "total": 0.12496189499961474, "count": 1, "self": 0.12496189499961474 } } } } } } }