{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3980950117111206, "min": 1.3980950117111206, "max": 1.4242949485778809, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70296.21875, "min": 68726.1484375, "max": 75965.09375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 75.36544342507645, "min": 73.2555720653789, "max": 372.96268656716416, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49289.0, "min": 49267.0, "max": 49977.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999909.0, "min": 49686.0, "max": 1999909.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999909.0, "min": 49686.0, "max": 1999909.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5129048824310303, "min": 0.09389971941709518, "max": 2.5404438972473145, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1643.4398193359375, "min": 12.488662719726562, "max": 1652.181396484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9071398916047646, "min": 1.8822488753419173, "max": 4.042346194765573, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2555.269489109516, "min": 250.339100420475, "max": 2615.3537958860397, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9071398916047646, "min": 1.8822488753419173, "max": 4.042346194765573, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2555.269489109516, "min": 250.339100420475, "max": 2615.3537958860397, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01703277716555426, "min": 0.012825976380660601, "max": 0.018867098511287216, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05109833149666278, "min": 0.025651952761321203, "max": 0.05660129553386165, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05790998546613587, "min": 0.02218284647290905, "max": 0.06021019505957763, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1737299563984076, "min": 0.0443656929458181, "max": 0.1737299563984076, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8007487331166724e-06, "min": 3.8007487331166724e-06, "max": 0.00029534820155059996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1402246199350017e-05, "min": 1.1402246199350017e-05, "max": 0.0008438748187084, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126688333333335, "min": 0.10126688333333335, "max": 0.1984494, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380065000000006, "min": 0.20766615000000005, "max": 0.5812916, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.321747833333343e-05, "min": 7.321747833333343e-05, "max": 0.004922625059999998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002196524350000003, "min": 0.0002196524350000003, "max": 0.014066450840000001, "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": "1670531198", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1670533429" }, "total": 2230.31652209, "count": 1, "self": 0.39941835499985245, "children": { "run_training.setup": { "total": 0.10654265300001953, "count": 1, "self": 0.10654265300001953 }, "TrainerController.start_learning": { "total": 2229.8105610820003, "count": 1, "self": 3.9128130049912215, "children": { "TrainerController._reset_env": { "total": 10.12844045700001, "count": 1, "self": 10.12844045700001 }, "TrainerController.advance": { "total": 2215.6593243560087, "count": 233316, "self": 4.279298772099082, "children": { "env_step": { "total": 1729.7847705229194, "count": 233316, "self": 1452.811593210775, "children": { "SubprocessEnvManager._take_step": { "total": 274.33061883402763, "count": 233316, "self": 14.205236476919936, "children": { "TorchPolicy.evaluate": { "total": 260.1253823571077, "count": 222958, "self": 65.74718391993645, "children": { "TorchPolicy.sample_actions": { "total": 194.37819843717125, "count": 222958, "self": 194.37819843717125 } } } } }, "workers": { "total": 2.6425584781167117, "count": 233316, "self": 0.0, "children": { "worker_root": { "total": 2222.1542805508498, "count": 233316, "is_parallel": true, "self": 1029.511420239875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019866650000039954, "count": 1, "is_parallel": true, "self": 0.00032165499999337044, "children": { "_process_rank_one_or_two_observation": { "total": 0.001665010000010625, "count": 2, "is_parallel": true, "self": 0.001665010000010625 } } }, "UnityEnvironment.step": { "total": 0.026761427999986154, "count": 1, "is_parallel": true, "self": 0.00026273700007095613, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018094699998982833, "count": 1, "is_parallel": true, "self": 0.00018094699998982833 }, "communicator.exchange": { "total": 0.025596855000003416, "count": 1, "is_parallel": true, "self": 0.025596855000003416 }, "steps_from_proto": { "total": 0.0007208889999219537, "count": 1, "is_parallel": true, "self": 0.000259331999927781, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046155699999417266, "count": 2, "is_parallel": true, "self": 0.00046155699999417266 } } } } } } }, "UnityEnvironment.step": { "total": 1192.6428603109748, "count": 233315, "is_parallel": true, "self": 34.25779670293309, "children": { "UnityEnvironment._generate_step_input": { "total": 73.27857550209217, "count": 233315, "is_parallel": true, "self": 73.27857550209217 }, "communicator.exchange": { "total": 994.1012666260385, "count": 233315, "is_parallel": true, "self": 994.1012666260385 }, "steps_from_proto": { "total": 91.00522147991092, "count": 233315, "is_parallel": true, "self": 37.468533564982295, "children": { "_process_rank_one_or_two_observation": { "total": 53.53668791492862, "count": 466630, "is_parallel": true, "self": 53.53668791492862 } } } } } } } } } } }, "trainer_advance": { "total": 481.5952550609903, "count": 233316, "self": 5.845059868987278, "children": { "process_trajectory": { "total": 154.21858887500093, "count": 233316, "self": 153.75538251600165, "children": { "RLTrainer._checkpoint": { "total": 0.46320635899928675, "count": 4, "self": 0.46320635899928675 } } }, "_update_policy": { "total": 321.5316063170021, "count": 97, "self": 267.75904209400926, "children": { "TorchPPOOptimizer.update": { "total": 53.772564222992855, "count": 2910, "self": 53.772564222992855 } } } } } } }, "trainer_threads": { "total": 1.0020003173849545e-06, "count": 1, "self": 1.0020003173849545e-06 }, "TrainerController._save_models": { "total": 0.10998226199990313, "count": 1, "self": 0.0026170740002271486, "children": { "RLTrainer._checkpoint": { "total": 0.10736518799967598, "count": 1, "self": 0.10736518799967598 } } } } } } }