{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4106389284133911, "min": 1.4106389284133911, "max": 1.426804542541504, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70651.8515625, "min": 69287.0859375, "max": 77676.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.6687402799378, "min": 69.7758865248227, "max": 416.3471074380165, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49298.0, "min": 49192.0, "max": 50378.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999955.0, "min": 49749.0, "max": 1999955.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999955.0, "min": 49749.0, "max": 1999955.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5191328525543213, "min": -0.0357179157435894, "max": 2.5198822021484375, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1619.802490234375, "min": -4.286149978637695, "max": 1764.00244140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.923096710471306, "min": 1.8294959542651972, "max": 4.022979872998285, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2522.55118483305, "min": 219.53951451182365, "max": 2731.1769699454308, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.923096710471306, "min": 1.8294959542651972, "max": 4.022979872998285, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2522.55118483305, "min": 219.53951451182365, "max": 2731.1769699454308, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015898065453964386, "min": 0.012524290055504633, "max": 0.020067471600486896, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04769419636189316, "min": 0.025048580111009265, "max": 0.059220782085321846, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06197195318010118, "min": 0.02519139740616083, "max": 0.067307034569482, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18591585954030354, "min": 0.05038279481232166, "max": 0.18758839045961698, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.862248712616666e-06, "min": 3.862248712616666e-06, "max": 0.000295357876547375, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1586746137849997e-05, "min": 1.1586746137849997e-05, "max": 0.0008440738686420499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128738333333336, "min": 0.10128738333333336, "max": 0.19845262500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30386215000000005, "min": 0.20771414999999996, "max": 0.5813579500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.424042833333333e-05, "min": 7.424042833333333e-05, "max": 0.004922785987500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022272128499999997, "min": 0.00022272128499999997, "max": 0.014069761705000003, "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": "1694631388", "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": "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": "1694633789" }, "total": 2400.4736321679998, "count": 1, "self": 0.4450837090003006, "children": { "run_training.setup": { "total": 0.04457961899993279, "count": 1, "self": 0.04457961899993279 }, "TrainerController.start_learning": { "total": 2399.9839688399998, "count": 1, "self": 4.309614270961447, "children": { "TrainerController._reset_env": { "total": 4.1691406859999915, "count": 1, "self": 4.1691406859999915 }, "TrainerController.advance": { "total": 2391.3846699190385, "count": 233256, "self": 4.443140151075113, "children": { "env_step": { "total": 1843.4796532380246, "count": 233256, "self": 1557.7063651769479, "children": { "SubprocessEnvManager._take_step": { "total": 282.89957209206875, "count": 233256, "self": 16.068604788072435, "children": { "TorchPolicy.evaluate": { "total": 266.8309673039963, "count": 222932, "self": 266.8309673039963 } } }, "workers": { "total": 2.8737159690080034, "count": 233256, "self": 0.0, "children": { "worker_root": { "total": 2392.5274589639835, "count": 233256, "is_parallel": true, "self": 1119.0837192899758, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009748259999469155, "count": 1, "is_parallel": true, "self": 0.00026606299991271953, "children": { "_process_rank_one_or_two_observation": { "total": 0.000708763000034196, "count": 2, "is_parallel": true, "self": 0.000708763000034196 } } }, "UnityEnvironment.step": { "total": 0.02871428699995704, "count": 1, "is_parallel": true, "self": 0.0003301669999018486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000237093000009736, "count": 1, "is_parallel": true, "self": 0.000237093000009736 }, "communicator.exchange": { "total": 0.02741675499999019, "count": 1, "is_parallel": true, "self": 0.02741675499999019 }, "steps_from_proto": { "total": 0.0007302720000552654, "count": 1, "is_parallel": true, "self": 0.00020444300002964155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005258290000256238, "count": 2, "is_parallel": true, "self": 0.0005258290000256238 } } } } } } }, "UnityEnvironment.step": { "total": 1273.4437396740077, "count": 233255, "is_parallel": true, "self": 39.77294646813857, "children": { "UnityEnvironment._generate_step_input": { "total": 80.42938483302203, "count": 233255, "is_parallel": true, "self": 80.42938483302203 }, "communicator.exchange": { "total": 1055.887626285921, "count": 233255, "is_parallel": true, "self": 1055.887626285921 }, "steps_from_proto": { "total": 97.35378208692623, "count": 233255, "is_parallel": true, "self": 34.642037725930436, "children": { "_process_rank_one_or_two_observation": { "total": 62.711744360995795, "count": 466510, "is_parallel": true, "self": 62.711744360995795 } } } } } } } } } } }, "trainer_advance": { "total": 543.4618765299388, "count": 233256, "self": 6.480220414048404, "children": { "process_trajectory": { "total": 139.95562243688858, "count": 233256, "self": 138.58186050888878, "children": { "RLTrainer._checkpoint": { "total": 1.3737619279997944, "count": 10, "self": 1.3737619279997944 } } }, "_update_policy": { "total": 397.0260336790018, "count": 97, "self": 338.31661259099155, "children": { "TorchPPOOptimizer.update": { "total": 58.70942108801023, "count": 2910, "self": 58.70942108801023 } } } } } } }, "trainer_threads": { "total": 9.099999260797631e-07, "count": 1, "self": 9.099999260797631e-07 }, "TrainerController._save_models": { "total": 0.12054305399988152, "count": 1, "self": 0.0019632549997368187, "children": { "RLTrainer._checkpoint": { "total": 0.1185797990001447, "count": 1, "self": 0.1185797990001447 } } } } } } }