{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4093490839004517, "min": 1.4093490839004517, "max": 1.4292089939117432, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70829.65625, "min": 69088.90625, "max": 75245.59375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.51361161524501, "min": 78.81948881789137, "max": 394.33858267716533, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49873.0, "min": 48945.0, "max": 50081.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999696.0, "min": 49948.0, "max": 1999696.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999696.0, "min": 49948.0, "max": 1999696.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4807634353637695, "min": 0.2844201624393463, "max": 2.5081307888031006, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1366.900634765625, "min": 35.83694076538086, "max": 1526.9285888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9304276875705337, "min": 1.8940830021387054, "max": 4.0392985398858885, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2165.665655851364, "min": 238.6544582694769, "max": 2427.6303545236588, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9304276875705337, "min": 1.8940830021387054, "max": 4.0392985398858885, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2165.665655851364, "min": 238.6544582694769, "max": 2427.6303545236588, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015360751218718683, "min": 0.014235382799233776, "max": 0.019775656243857357, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04608225365615605, "min": 0.02946040750151345, "max": 0.059326968731572075, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0522826164133019, "min": 0.019943995804836353, "max": 0.05882013912002246, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1568478492399057, "min": 0.039887991609672706, "max": 0.17646041736006737, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.660248779949985e-06, "min": 3.660248779949985e-06, "max": 0.00029538000153999993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0980746339849955e-05, "min": 1.0980746339849955e-05, "max": 0.0008441347686217501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122005, "min": 0.10122005, "max": 0.19845999999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366015, "min": 0.20760335, "max": 0.5813782499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.088049499999974e-05, "min": 7.088049499999974e-05, "max": 0.004923154, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002126414849999992, "min": 0.0002126414849999992, "max": 0.014070774674999995, "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": "1713295974", "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=Huggy3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713298442" }, "total": 2467.456751945, "count": 1, "self": 0.7045752320004794, "children": { "run_training.setup": { "total": 0.049732330000097136, "count": 1, "self": 0.049732330000097136 }, "TrainerController.start_learning": { "total": 2466.7024443829996, "count": 1, "self": 4.503706265049459, "children": { "TrainerController._reset_env": { "total": 1.8901388449999104, "count": 1, "self": 1.8901388449999104 }, "TrainerController.advance": { "total": 2460.1429081709502, "count": 232883, "self": 4.797697899910418, "children": { "env_step": { "total": 1970.447363331025, "count": 232883, "self": 1636.5180583122208, "children": { "SubprocessEnvManager._take_step": { "total": 330.89315508489904, "count": 232883, "self": 16.759603147953158, "children": { "TorchPolicy.evaluate": { "total": 314.1335519369459, "count": 223004, "self": 314.1335519369459 } } }, "workers": { "total": 3.036149933905108, "count": 232883, "self": 0.0, "children": { "worker_root": { "total": 2459.1622232510936, "count": 232883, "is_parallel": true, "self": 1138.4000378471364, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008755989999826852, "count": 1, "is_parallel": true, "self": 0.0002305670002442639, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006450319997384213, "count": 2, "is_parallel": true, "self": 0.0006450319997384213 } } }, "UnityEnvironment.step": { "total": 0.030808140000090134, "count": 1, "is_parallel": true, "self": 0.0003765870001188887, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021444899994094158, "count": 1, "is_parallel": true, "self": 0.00021444899994094158 }, "communicator.exchange": { "total": 0.02944750799997564, "count": 1, "is_parallel": true, "self": 0.02944750799997564 }, "steps_from_proto": { "total": 0.000769596000054662, "count": 1, "is_parallel": true, "self": 0.0002327780002815416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005368179997731204, "count": 2, "is_parallel": true, "self": 0.0005368179997731204 } } } } } } }, "UnityEnvironment.step": { "total": 1320.7621854039571, "count": 232882, "is_parallel": true, "self": 40.27159508211912, "children": { "UnityEnvironment._generate_step_input": { "total": 88.46376639489222, "count": 232882, "is_parallel": true, "self": 88.46376639489222 }, "communicator.exchange": { "total": 1097.4546976000197, "count": 232882, "is_parallel": true, "self": 1097.4546976000197 }, "steps_from_proto": { "total": 94.57212632692608, "count": 232882, "is_parallel": true, "self": 36.18435211975088, "children": { "_process_rank_one_or_two_observation": { "total": 58.3877742071752, "count": 465764, "is_parallel": true, "self": 58.3877742071752 } } } } } } } } } } }, "trainer_advance": { "total": 484.8978469400149, "count": 232883, "self": 6.380783935017689, "children": { "process_trajectory": { "total": 162.4180026999968, "count": 232883, "self": 161.08960551299697, "children": { "RLTrainer._checkpoint": { "total": 1.3283971869998368, "count": 10, "self": 1.3283971869998368 } } }, "_update_policy": { "total": 316.0990603050004, "count": 97, "self": 254.96259744499935, "children": { "TorchPPOOptimizer.update": { "total": 61.136462860001075, "count": 2910, "self": 61.136462860001075 } } } } } } }, "trainer_threads": { "total": 1.249999968422344e-06, "count": 1, "self": 1.249999968422344e-06 }, "TrainerController._save_models": { "total": 0.16568985200001407, "count": 1, "self": 0.002950919999875623, "children": { "RLTrainer._checkpoint": { "total": 0.16273893200013845, "count": 1, "self": 0.16273893200013845 } } } } } } }