{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4033819437026978, "min": 1.4033747911453247, "max": 1.4275586605072021, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69853.3359375, "min": 68540.453125, "max": 78830.7578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 105.62367864693447, "min": 97.61584158415842, "max": 401.168, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49960.0, "min": 48961.0, "max": 50146.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999726.0, "min": 49824.0, "max": 1999726.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999726.0, "min": 49824.0, "max": 1999726.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3019931316375732, "min": 0.14354026317596436, "max": 2.388298511505127, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1091.144775390625, "min": 17.798992156982422, "max": 1161.8740234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5545063858796775, "min": 1.8017750444912142, "max": 3.8006572840334494, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1684.8360269069672, "min": 223.42010551691055, "max": 1843.5372132062912, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5545063858796775, "min": 1.8017750444912142, "max": 3.8006572840334494, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1684.8360269069672, "min": 223.42010551691055, "max": 1843.5372132062912, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016888853096558402, "min": 0.013880279854735514, "max": 0.020808902922565015, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.033777706193116805, "min": 0.027760559709471028, "max": 0.062426708767695044, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05312898730238279, "min": 0.02071679200356205, "max": 0.05523988778392474, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10625797460476558, "min": 0.0414335840071241, "max": 0.1600521596769492, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.424948525050008e-06, "min": 4.424948525050008e-06, "max": 0.00029531602656132503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.849897050100017e-06, "min": 8.849897050100017e-06, "max": 0.00084371056876315, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10147494999999998, "min": 0.10147494999999998, "max": 0.19843867500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20294989999999996, "min": 0.20294989999999996, "max": 0.5812368500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.360000500000011e-05, "min": 8.360000500000011e-05, "max": 0.004922089882500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016720001000000023, "min": 0.00016720001000000023, "max": 0.014063718815000003, "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": "1768052779", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1768055354" }, "total": 2574.6764019989996, "count": 1, "self": 0.4812285120001434, "children": { "run_training.setup": { "total": 0.028147833999923932, "count": 1, "self": 0.028147833999923932 }, "TrainerController.start_learning": { "total": 2574.1670256529997, "count": 1, "self": 4.343995195889875, "children": { "TrainerController._reset_env": { "total": 2.8294495779999806, "count": 1, "self": 2.8294495779999806 }, "TrainerController.advance": { "total": 2566.8792157301095, "count": 231153, "self": 4.419383356978415, "children": { "env_step": { "total": 2106.7299210780347, "count": 231153, "self": 1694.8540729731262, "children": { "SubprocessEnvManager._take_step": { "total": 409.12866558199573, "count": 231153, "self": 15.243315099863139, "children": { "TorchPolicy.evaluate": { "total": 393.8853504821326, "count": 222980, "self": 393.8853504821326 } } }, "workers": { "total": 2.747182522912908, "count": 231153, "self": 0.0, "children": { "worker_root": { "total": 2561.788825369038, "count": 231153, "is_parallel": true, "self": 1186.660246594975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000903504999996585, "count": 1, "is_parallel": true, "self": 0.00028884999994716054, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006146550000494244, "count": 2, "is_parallel": true, "self": 0.0006146550000494244 } } }, "UnityEnvironment.step": { "total": 0.030824184000039168, "count": 1, "is_parallel": true, "self": 0.00036086700004034356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019505000000208383, "count": 1, "is_parallel": true, "self": 0.00019505000000208383 }, "communicator.exchange": { "total": 0.029564256999947247, "count": 1, "is_parallel": true, "self": 0.029564256999947247 }, "steps_from_proto": { "total": 0.0007040100000494931, "count": 1, "is_parallel": true, "self": 0.00018584700001156307, "children": { "_process_rank_one_or_two_observation": { "total": 0.00051816300003793, "count": 2, "is_parallel": true, "self": 0.00051816300003793 } } } } } } }, "UnityEnvironment.step": { "total": 1375.128578774063, "count": 231152, "is_parallel": true, "self": 38.98793411900897, "children": { "UnityEnvironment._generate_step_input": { "total": 86.18706240003348, "count": 231152, "is_parallel": true, "self": 86.18706240003348 }, "communicator.exchange": { "total": 1157.9496758420544, "count": 231152, "is_parallel": true, "self": 1157.9496758420544 }, "steps_from_proto": { "total": 92.00390641296633, "count": 231152, "is_parallel": true, "self": 33.11722902095937, "children": { "_process_rank_one_or_two_observation": { "total": 58.88667739200696, "count": 462304, "is_parallel": true, "self": 58.88667739200696 } } } } } } } } } } }, "trainer_advance": { "total": 455.7299112950964, "count": 231153, "self": 6.552573110093476, "children": { "process_trajectory": { "total": 148.1381008190018, "count": 231153, "self": 146.9104525870017, "children": { "RLTrainer._checkpoint": { "total": 1.2276482320000923, "count": 10, "self": 1.2276482320000923 } } }, "_update_policy": { "total": 301.0392373660011, "count": 96, "self": 239.35173363801107, "children": { "TorchPPOOptimizer.update": { "total": 61.68750372799002, "count": 2880, "self": 61.68750372799002 } } } } } } }, "trainer_threads": { "total": 8.219999472203199e-07, "count": 1, "self": 8.219999472203199e-07 }, "TrainerController._save_models": { "total": 0.11436432700020305, "count": 1, "self": 0.0018914960000984138, "children": { "RLTrainer._checkpoint": { "total": 0.11247283100010463, "count": 1, "self": 0.11247283100010463 } } } } } } }