{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3983099460601807, "min": 1.3983099460601807, "max": 1.4253803491592407, "count": 35 }, "Huggy.Policy.Entropy.sum": { "value": 68830.40625, "min": 67765.46875, "max": 76182.671875, "count": 35 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.49795081967213, "min": 95.27745664739885, "max": 415.76666666666665, "count": 35 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49531.0, "min": 48982.0, "max": 50226.0, "count": 35 }, "Huggy.Step.mean": { "value": 1749971.0, "min": 49262.0, "max": 1749971.0, "count": 35 }, "Huggy.Step.sum": { "value": 1749971.0, "min": 49262.0, "max": 1749971.0, "count": 35 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.306255340576172, "min": 0.045007023960351944, "max": 2.4212141036987305, "count": 35 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1125.45263671875, "min": 5.355835914611816, "max": 1204.531982421875, "count": 35 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5001281852849195, "min": 1.8158302171891476, "max": 3.8890362209772906, "count": 35 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1708.0625544190407, "min": 216.08379584550858, "max": 1913.754614830017, "count": 35 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5001281852849195, "min": 1.8158302171891476, "max": 3.8890362209772906, "count": 35 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1708.0625544190407, "min": 216.08379584550858, "max": 1913.754614830017, "count": 35 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018456456429945926, "min": 0.014081007061273946, "max": 0.019941337537279145, "count": 35 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03691291285989185, "min": 0.028324599144252716, "max": 0.05982401261183744, "count": 35 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04841971403608719, "min": 0.023191223448763294, "max": 0.05542781228820483, "count": 35 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09683942807217438, "min": 0.04638244689752659, "max": 0.1620821355531613, "count": 35 }, "Huggy.Policy.LearningRate.mean": { "value": 4.183051105652499e-05, "min": 4.183051105652499e-05, "max": 0.00029536695154434996, "count": 35 }, "Huggy.Policy.LearningRate.sum": { "value": 8.366102211304998e-05, "min": 8.366102211304998e-05, "max": 0.0008442925685691503, "count": 35 }, "Huggy.Policy.Epsilon.mean": { "value": 0.11394347499999999, "min": 0.11394347499999999, "max": 0.19845565, "count": 35 }, "Huggy.Policy.Epsilon.sum": { "value": 0.22788694999999998, "min": 0.22788694999999998, "max": 0.58143085, "count": 35 }, "Huggy.Policy.Beta.mean": { "value": 0.0007057794025000001, "min": 0.0007057794025000001, "max": 0.0049229369349999995, "count": 35 }, "Huggy.Policy.Beta.sum": { "value": 0.0014115588050000003, "min": 0.0014115588050000003, "max": 0.014073399415000002, "count": 35 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700138269", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700140444" }, "total": 2175.39972761, "count": 1, "self": 0.5385254489997351, "children": { "run_training.setup": { "total": 0.045974872000016376, "count": 1, "self": 0.045974872000016376 }, "TrainerController.start_learning": { "total": 2174.815227289, "count": 1, "self": 3.803259855969827, "children": { "TrainerController._reset_env": { "total": 8.901600932000008, "count": 1, "self": 8.901600932000008 }, "TrainerController.advance": { "total": 2161.8543841240307, "count": 207463, "self": 4.045135396021578, "children": { "env_step": { "total": 1714.4052350280315, "count": 207463, "self": 1415.8633434149724, "children": { "SubprocessEnvManager._take_step": { "total": 296.0181824400771, "count": 207463, "self": 14.823111376039378, "children": { "TorchPolicy.evaluate": { "total": 281.19507106403773, "count": 199944, "self": 281.19507106403773 } } }, "workers": { "total": 2.523709172982109, "count": 207463, "self": 0.0, "children": { "worker_root": { "total": 2165.6558484329526, "count": 207463, "is_parallel": true, "self": 1014.0603099709756, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008892230000014933, "count": 1, "is_parallel": true, "self": 0.0002743750000036016, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006148479999978917, "count": 2, "is_parallel": true, "self": 0.0006148479999978917 } } }, "UnityEnvironment.step": { "total": 0.0317659079999828, "count": 1, "is_parallel": true, "self": 0.00031374399998185254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021288799999297225, "count": 1, "is_parallel": true, "self": 0.00021288799999297225 }, "communicator.exchange": { "total": 0.03052069500000698, "count": 1, "is_parallel": true, "self": 0.03052069500000698 }, "steps_from_proto": { "total": 0.0007185810000009951, "count": 1, "is_parallel": true, "self": 0.00020432900001310372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005142519999878914, "count": 2, "is_parallel": true, "self": 0.0005142519999878914 } } } } } } }, "UnityEnvironment.step": { "total": 1151.595538461977, "count": 207462, "is_parallel": true, "self": 35.84665910885701, "children": { "UnityEnvironment._generate_step_input": { "total": 73.77596329302611, "count": 207462, "is_parallel": true, "self": 73.77596329302611 }, "communicator.exchange": { "total": 962.0795654280455, "count": 207462, "is_parallel": true, "self": 962.0795654280455 }, "steps_from_proto": { "total": 79.8933506320484, "count": 207462, "is_parallel": true, "self": 28.08747226292428, "children": { "_process_rank_one_or_two_observation": { "total": 51.805878369124116, "count": 414924, "is_parallel": true, "self": 51.805878369124116 } } } } } } } } } } }, "trainer_advance": { "total": 443.4040136999779, "count": 207463, "self": 5.749397096944449, "children": { "process_trajectory": { "total": 131.16116423303365, "count": 207463, "self": 130.2220014550334, "children": { "RLTrainer._checkpoint": { "total": 0.9391627780002523, "count": 8, "self": 0.9391627780002523 } } }, "_update_policy": { "total": 306.4934523699998, "count": 87, "self": 250.62865507199828, "children": { "TorchPPOOptimizer.update": { "total": 55.86479729800149, "count": 2590, "self": 55.86479729800149 } } } } } } }, "trainer_threads": { "total": 7.77000013840734e-06, "count": 1, "self": 7.77000013840734e-06 }, "TrainerController._save_models": { "total": 0.2559746069996436, "count": 1, "self": 0.002724166999996669, "children": { "RLTrainer._checkpoint": { "total": 0.2532504399996469, "count": 1, "self": 0.2532504399996469 } } } } } } }