{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054083824157715, "min": 1.4054083824157715, "max": 1.430415391921997, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69536.796875, "min": 68415.4140625, "max": 77195.8671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.92172211350294, "min": 85.3747841105354, "max": 419.3193277310924, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49527.0, "min": 48988.0, "max": 50047.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49525.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49525.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3738739490509033, "min": 0.046862684190273285, "max": 2.469106912612915, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1213.049560546875, "min": 5.529796600341797, "max": 1381.7841796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6115861939824025, "min": 1.776599552166664, "max": 3.8874299501060348, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1845.5205451250076, "min": 209.63874715566635, "max": 2206.7083295583725, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6115861939824025, "min": 1.776599552166664, "max": 3.8874299501060348, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1845.5205451250076, "min": 209.63874715566635, "max": 2206.7083295583725, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015878399456738006, "min": 0.013726398584549316, "max": 0.020884640329879606, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047635198370214016, "min": 0.027452797169098632, "max": 0.06265392098963882, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054061354903711216, "min": 0.021511860191822052, "max": 0.06608146677414577, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16218406471113364, "min": 0.043023720383644104, "max": 0.18227180639902751, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4293988568999914e-06, "min": 3.4293988568999914e-06, "max": 0.00029537407654197496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0288196570699975e-05, "min": 1.0288196570699975e-05, "max": 0.0008444434685188501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011431, "min": 0.1011431, "max": 0.19845802499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034293, "min": 0.20749170000000006, "max": 0.5814811500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.704068999999984e-05, "min": 6.704068999999984e-05, "max": 0.004923055447499998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002011220699999995, "min": 0.0002011220699999995, "max": 0.014075909385, "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": "1699321743", "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": "1699324329" }, "total": 2585.801952617, "count": 1, "self": 0.6395271290002711, "children": { "run_training.setup": { "total": 0.048425070000121195, "count": 1, "self": 0.048425070000121195 }, "TrainerController.start_learning": { "total": 2585.1140004179997, "count": 1, "self": 4.81795924920516, "children": { "TrainerController._reset_env": { "total": 7.420227256999851, "count": 1, "self": 7.420227256999851 }, "TrainerController.advance": { "total": 2572.7262024727943, "count": 231956, "self": 5.053655717937545, "children": { "env_step": { "total": 2035.0661041079265, "count": 231956, "self": 1672.408413489866, "children": { "SubprocessEnvManager._take_step": { "total": 359.52248539797756, "count": 231956, "self": 17.83941655394483, "children": { "TorchPolicy.evaluate": { "total": 341.68306884403273, "count": 222966, "self": 341.68306884403273 } } }, "workers": { "total": 3.1352052200829803, "count": 231956, "self": 0.0, "children": { "worker_root": { "total": 2577.1792724261477, "count": 231956, "is_parallel": true, "self": 1218.4545819660746, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008490689999689494, "count": 1, "is_parallel": true, "self": 0.00023332199998549186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006157469999834575, "count": 2, "is_parallel": true, "self": 0.0006157469999834575 } } }, "UnityEnvironment.step": { "total": 0.03074551200006681, "count": 1, "is_parallel": true, "self": 0.0003281310000602389, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021966899998915324, "count": 1, "is_parallel": true, "self": 0.00021966899998915324 }, "communicator.exchange": { "total": 0.029466705000004367, "count": 1, "is_parallel": true, "self": 0.029466705000004367 }, "steps_from_proto": { "total": 0.0007310070000130509, "count": 1, "is_parallel": true, "self": 0.00022457600016423385, "children": { "_process_rank_one_or_two_observation": { "total": 0.000506430999848817, "count": 2, "is_parallel": true, "self": 0.000506430999848817 } } } } } } }, "UnityEnvironment.step": { "total": 1358.7246904600731, "count": 231955, "is_parallel": true, "self": 41.452270938985976, "children": { "UnityEnvironment._generate_step_input": { "total": 91.78885214804859, "count": 231955, "is_parallel": true, "self": 91.78885214804859 }, "communicator.exchange": { "total": 1129.7667336649843, "count": 231955, "is_parallel": true, "self": 1129.7667336649843 }, "steps_from_proto": { "total": 95.71683370805431, "count": 231955, "is_parallel": true, "self": 36.179956016159394, "children": { "_process_rank_one_or_two_observation": { "total": 59.536877691894915, "count": 463910, "is_parallel": true, "self": 59.536877691894915 } } } } } } } } } } }, "trainer_advance": { "total": 532.60644264693, "count": 231956, "self": 7.404472675855914, "children": { "process_trajectory": { "total": 160.70384616907268, "count": 231956, "self": 159.44714833307285, "children": { "RLTrainer._checkpoint": { "total": 1.2566978359998302, "count": 10, "self": 1.2566978359998302 } } }, "_update_policy": { "total": 364.4981238020014, "count": 97, "self": 299.69745789898866, "children": { "TorchPPOOptimizer.update": { "total": 64.80066590301271, "count": 2910, "self": 64.80066590301271 } } } } } } }, "trainer_threads": { "total": 1.3270000636111945e-06, "count": 1, "self": 1.3270000636111945e-06 }, "TrainerController._save_models": { "total": 0.14961011200011853, "count": 1, "self": 0.002846471000339079, "children": { "RLTrainer._checkpoint": { "total": 0.14676364099977945, "count": 1, "self": 0.14676364099977945 } } } } } } }