{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40531587600708, "min": 1.40531587600708, "max": 1.4267265796661377, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68825.34375, "min": 68825.34375, "max": 77527.90625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.76101694915255, "min": 75.34045801526717, "max": 373.82089552238807, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49419.0, "min": 49001.0, "max": 50092.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999946.0, "min": 49854.0, "max": 1999946.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999946.0, "min": 49854.0, "max": 1999946.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4231033325195312, "min": 0.14278125762939453, "max": 2.5524377822875977, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1429.6309814453125, "min": 18.98990821838379, "max": 1624.397216796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6454997630442603, "min": 1.944331529445218, "max": 4.105185155073801, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2150.8448601961136, "min": 258.596093416214, "max": 2576.4084490537643, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6454997630442603, "min": 1.944331529445218, "max": 4.105185155073801, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2150.8448601961136, "min": 258.596093416214, "max": 2576.4084490537643, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016261804897092388, "min": 0.014261684922773082, "max": 0.0200353690606183, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04878541469127716, "min": 0.028800639651550834, "max": 0.056755361011407025, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.058675614454680024, "min": 0.023043460585176943, "max": 0.06645332518965005, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17602684336404006, "min": 0.04608692117035389, "max": 0.19251388497650623, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7621987459666558e-06, "min": 3.7621987459666558e-06, "max": 0.0002953333515555499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1286596237899968e-05, "min": 1.1286596237899968e-05, "max": 0.0008440489686503498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125403333333331, "min": 0.10125403333333331, "max": 0.19844444999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037620999999999, "min": 0.20766639999999997, "max": 0.5813496499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.257626333333318e-05, "min": 7.257626333333318e-05, "max": 0.004922378055000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021772878999999954, "min": 0.00021772878999999954, "max": 0.014069347535000002, "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": "1689072372", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1689074798" }, "total": 2425.9845332, "count": 1, "self": 0.45267384299995683, "children": { "run_training.setup": { "total": 0.042708489999995436, "count": 1, "self": 0.042708489999995436 }, "TrainerController.start_learning": { "total": 2425.489150867, "count": 1, "self": 4.243713178964299, "children": { "TrainerController._reset_env": { "total": 4.235075359000007, "count": 1, "self": 4.235075359000007 }, "TrainerController.advance": { "total": 2416.8890548110357, "count": 233229, "self": 4.511611115067353, "children": { "env_step": { "total": 1871.4132413270659, "count": 233229, "self": 1581.647677949102, "children": { "SubprocessEnvManager._take_step": { "total": 286.9863563999279, "count": 233229, "self": 16.552376961915, "children": { "TorchPolicy.evaluate": { "total": 270.4339794380129, "count": 223018, "self": 270.4339794380129 } } }, "workers": { "total": 2.7792069780359725, "count": 233229, "self": 0.0, "children": { "worker_root": { "total": 2417.8543415110134, "count": 233229, "is_parallel": true, "self": 1127.6212344749274, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008494630000086545, "count": 1, "is_parallel": true, "self": 0.00025606300005165394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005933999999570005, "count": 2, "is_parallel": true, "self": 0.0005933999999570005 } } }, "UnityEnvironment.step": { "total": 0.03021679599999061, "count": 1, "is_parallel": true, "self": 0.0003256610001471927, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020441599997411686, "count": 1, "is_parallel": true, "self": 0.00020441599997411686 }, "communicator.exchange": { "total": 0.02895292799996696, "count": 1, "is_parallel": true, "self": 0.02895292799996696 }, "steps_from_proto": { "total": 0.0007337909999023395, "count": 1, "is_parallel": true, "self": 0.00019838199989408167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005354090000082579, "count": 2, "is_parallel": true, "self": 0.0005354090000082579 } } } } } } }, "UnityEnvironment.step": { "total": 1290.233107036086, "count": 233228, "is_parallel": true, "self": 39.428397883197704, "children": { "UnityEnvironment._generate_step_input": { "total": 79.87330926196091, "count": 233228, "is_parallel": true, "self": 79.87330926196091 }, "communicator.exchange": { "total": 1073.1278360150104, "count": 233228, "is_parallel": true, "self": 1073.1278360150104 }, "steps_from_proto": { "total": 97.80356387591712, "count": 233228, "is_parallel": true, "self": 34.47346892286009, "children": { "_process_rank_one_or_two_observation": { "total": 63.33009495305703, "count": 466456, "is_parallel": true, "self": 63.33009495305703 } } } } } } } } } } }, "trainer_advance": { "total": 540.9642023689025, "count": 233229, "self": 6.268506377955987, "children": { "process_trajectory": { "total": 140.09487025194596, "count": 233229, "self": 138.75764365294583, "children": { "RLTrainer._checkpoint": { "total": 1.3372265990001324, "count": 10, "self": 1.3372265990001324 } } }, "_update_policy": { "total": 394.6008257390006, "count": 97, "self": 334.29560977699316, "children": { "TorchPPOOptimizer.update": { "total": 60.30521596200742, "count": 2910, "self": 60.30521596200742 } } } } } } }, "trainer_threads": { "total": 1.1069996617152356e-06, "count": 1, "self": 1.1069996617152356e-06 }, "TrainerController._save_models": { "total": 0.12130641100020512, "count": 1, "self": 0.001990427000237105, "children": { "RLTrainer._checkpoint": { "total": 0.11931598399996801, "count": 1, "self": 0.11931598399996801 } } } } } } }