{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4023487567901611, "min": 1.4023487567901611, "max": 1.425593614578247, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69273.2265625, "min": 68649.9921875, "max": 77500.2734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.02521008403362, "min": 80.46818923327896, "max": 399.816, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49400.0, "min": 49222.0, "max": 50157.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999884.0, "min": 49614.0, "max": 1999884.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999884.0, "min": 49614.0, "max": 1999884.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.432745933532715, "min": -0.06736146658658981, "max": 2.506398916244507, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1447.4837646484375, "min": -8.352822303771973, "max": 1498.40234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7900287925696174, "min": 1.6914764259371065, "max": 3.9311200798371546, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2255.0671315789223, "min": 209.7430768162012, "max": 2358.7303805351257, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7900287925696174, "min": 1.6914764259371065, "max": 3.9311200798371546, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2255.0671315789223, "min": 209.7430768162012, "max": 2358.7303805351257, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01740627661505035, "min": 0.013331913201060766, "max": 0.020794861835020127, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05221882984515105, "min": 0.026663826402121532, "max": 0.0594634785685533, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052301371221741035, "min": 0.023689921976377565, "max": 0.059065169468522076, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1569041136652231, "min": 0.04737984395275513, "max": 0.17719550840556622, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6604487798833352e-06, "min": 3.6604487798833352e-06, "max": 0.00029534407655197495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0981346339650005e-05, "min": 1.0981346339650005e-05, "max": 0.0008441404686198499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122011666666668, "min": 0.10122011666666668, "max": 0.19844802500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366035, "min": 0.20757225, "max": 0.58138015, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.088382166666668e-05, "min": 7.088382166666668e-05, "max": 0.0049225564475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021265146500000005, "min": 0.00021265146500000005, "max": 0.014070869484999998, "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": "1718559024", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718561369" }, "total": 2344.882421446, "count": 1, "self": 0.44070220600042376, "children": { "run_training.setup": { "total": 0.05855560500003776, "count": 1, "self": 0.05855560500003776 }, "TrainerController.start_learning": { "total": 2344.3831636349996, "count": 1, "self": 4.2334748079688325, "children": { "TrainerController._reset_env": { "total": 3.1080696479999688, "count": 1, "self": 3.1080696479999688 }, "TrainerController.advance": { "total": 2336.9275129100306, "count": 232624, "self": 4.647140157967442, "children": { "env_step": { "total": 1849.3494306770683, "count": 232624, "self": 1523.6138417031489, "children": { "SubprocessEnvManager._take_step": { "total": 323.0167982399871, "count": 232624, "self": 16.00677255795074, "children": { "TorchPolicy.evaluate": { "total": 307.01002568203637, "count": 222942, "self": 307.01002568203637 } } }, "workers": { "total": 2.7187907339323374, "count": 232624, "self": 0.0, "children": { "worker_root": { "total": 2337.4905203590133, "count": 232624, "is_parallel": true, "self": 1109.026201502106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009290890000102081, "count": 1, "is_parallel": true, "self": 0.00021947600009752932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007096129999126788, "count": 2, "is_parallel": true, "self": 0.0007096129999126788 } } }, "UnityEnvironment.step": { "total": 0.02980623700000251, "count": 1, "is_parallel": true, "self": 0.00041409300013128814, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002013459999261613, "count": 1, "is_parallel": true, "self": 0.0002013459999261613 }, "communicator.exchange": { "total": 0.028430640999999923, "count": 1, "is_parallel": true, "self": 0.028430640999999923 }, "steps_from_proto": { "total": 0.0007601569999451385, "count": 1, "is_parallel": true, "self": 0.00021068699982151884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005494700001236197, "count": 2, "is_parallel": true, "self": 0.0005494700001236197 } } } } } } }, "UnityEnvironment.step": { "total": 1228.4643188569073, "count": 232623, "is_parallel": true, "self": 38.58396719095481, "children": { "UnityEnvironment._generate_step_input": { "total": 78.83716134194276, "count": 232623, "is_parallel": true, "self": 78.83716134194276 }, "communicator.exchange": { "total": 1023.615515144064, "count": 232623, "is_parallel": true, "self": 1023.615515144064 }, "steps_from_proto": { "total": 87.42767517994571, "count": 232623, "is_parallel": true, "self": 30.690341713785415, "children": { "_process_rank_one_or_two_observation": { "total": 56.737333466160294, "count": 465246, "is_parallel": true, "self": 56.737333466160294 } } } } } } } } } } }, "trainer_advance": { "total": 482.93094207499485, "count": 232624, "self": 6.538654872987763, "children": { "process_trajectory": { "total": 155.99465458601026, "count": 232624, "self": 154.67489192800986, "children": { "RLTrainer._checkpoint": { "total": 1.3197626580003998, "count": 10, "self": 1.3197626580003998 } } }, "_update_policy": { "total": 320.3976326159968, "count": 97, "self": 257.54168458899073, "children": { "TorchPPOOptimizer.update": { "total": 62.85594802700609, "count": 2910, "self": 62.85594802700609 } } } } } } }, "trainer_threads": { "total": 1.229000190505758e-06, "count": 1, "self": 1.229000190505758e-06 }, "TrainerController._save_models": { "total": 0.11410504000014043, "count": 1, "self": 0.0018339769999329292, "children": { "RLTrainer._checkpoint": { "total": 0.1122710630002075, "count": 1, "self": 0.1122710630002075 } } } } } } }