{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3963216245174408, "min": 0.37892216444015503, "max": 1.4495625495910645, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12060.859375, "min": 11373.6796875, "max": 43973.9296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43158861994743347, "min": -0.0929163247346878, "max": 0.5519277453422546, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.39210510253906, "min": -22.392833709716797, "max": 154.53976440429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0027870223857462406, "min": -0.00042706672684289515, "max": 0.23599685728549957, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7580701112747192, "min": -0.11402681469917297, "max": 55.93125534057617, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06696148093582856, "min": 0.062427873386958585, "max": 0.07537894976558164, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0044222140374284, "min": 0.49671674601435284, "max": 1.1306842464837246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01608618958335784, "min": 0.000992208526063701, "max": 0.01623464779271439, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24129284375036758, "min": 0.0075454792245495655, "max": 0.24129284375036758, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.573997475366666e-06, "min": 7.573997475366666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011360996213049999, "min": 0.00011360996213049999, "max": 0.0035081249306250996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252463333333336, "min": 0.10252463333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378695000000004, "min": 1.3691136000000002, "max": 2.5693748999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026221087, "min": 0.00026221087, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003933163050000001, "min": 0.003933163050000001, "max": 0.11696055251, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00945773720741272, "min": 0.009271085262298584, "max": 0.3552553951740265, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1418660581111908, "min": 0.12979519367218018, "max": 2.486787796020508, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.5844155844156, "min": 361.8152173913044, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33540.0, "min": 15984.0, "max": 33540.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3825324446736993, "min": -1.0000000521540642, "max": 1.5077173760079818, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.45499823987484, "min": -32.000001668930054, "max": 138.70999859273434, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3825324446736993, "min": -1.0000000521540642, "max": 1.5077173760079818, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.45499823987484, "min": -32.000001668930054, "max": 138.70999859273434, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04263687019112411, "min": 0.03542026030481793, "max": 6.730314579792321, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2830390047165565, "min": 2.6668454946629936, "max": 107.68503327667713, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673709219", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1673711273" }, "total": 2053.37231426, "count": 1, "self": 0.487154233000183, "children": { "run_training.setup": { "total": 0.11296040399997764, "count": 1, "self": 0.11296040399997764 }, "TrainerController.start_learning": { "total": 2052.7721996230002, "count": 1, "self": 1.2402444569856925, "children": { "TrainerController._reset_env": { "total": 6.496398377999981, "count": 1, "self": 6.496398377999981 }, "TrainerController.advance": { "total": 2044.9392552420145, "count": 63764, "self": 1.307802944031664, "children": { "env_step": { "total": 1380.8280767199785, "count": 63764, "self": 1274.9483338659165, "children": { "SubprocessEnvManager._take_step": { "total": 105.10758953706988, "count": 63764, "self": 4.38078287908786, "children": { "TorchPolicy.evaluate": { "total": 100.72680665798202, "count": 62561, "self": 34.03783737599417, "children": { "TorchPolicy.sample_actions": { "total": 66.68896928198785, "count": 62561, "self": 66.68896928198785 } } } } }, "workers": { "total": 0.7721533169919894, "count": 63764, "self": 0.0, "children": { "worker_root": { "total": 2048.2412592330234, "count": 63764, "is_parallel": true, "self": 872.4286040499896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001805626999953347, "count": 1, "is_parallel": true, "self": 0.000685975999999755, "children": { "_process_rank_one_or_two_observation": { "total": 0.001119650999953592, "count": 8, "is_parallel": true, "self": 0.001119650999953592 } } }, "UnityEnvironment.step": { "total": 0.05277994700009003, "count": 1, "is_parallel": true, "self": 0.0005411750000803295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005054120000522744, "count": 1, "is_parallel": true, "self": 0.0005054120000522744 }, "communicator.exchange": { "total": 0.05002884099997118, "count": 1, "is_parallel": true, "self": 0.05002884099997118 }, "steps_from_proto": { "total": 0.0017045189999862487, "count": 1, "is_parallel": true, "self": 0.00046017399972697604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012443450002592726, "count": 8, "is_parallel": true, "self": 0.0012443450002592726 } } } } } } }, "UnityEnvironment.step": { "total": 1175.8126551830337, "count": 63763, "is_parallel": true, "self": 28.385981297061335, "children": { "UnityEnvironment._generate_step_input": { "total": 24.030136245979634, "count": 63763, "is_parallel": true, "self": 24.030136245979634 }, "communicator.exchange": { "total": 1017.9619269290041, "count": 63763, "is_parallel": true, "self": 1017.9619269290041 }, "steps_from_proto": { "total": 105.43461071098875, "count": 63763, "is_parallel": true, "self": 23.384566760032158, "children": { "_process_rank_one_or_two_observation": { "total": 82.05004395095659, "count": 510104, "is_parallel": true, "self": 82.05004395095659 } } } } } } } } } } }, "trainer_advance": { "total": 662.8033755780043, "count": 63764, "self": 2.202008867012296, "children": { "process_trajectory": { "total": 150.2878955409965, "count": 63764, "self": 150.0755036999965, "children": { "RLTrainer._checkpoint": { "total": 0.21239184099999875, "count": 2, "self": 0.21239184099999875 } } }, "_update_policy": { "total": 510.3134711699955, "count": 446, "self": 193.58307704400738, "children": { "TorchPPOOptimizer.update": { "total": 316.73039412598814, "count": 22773, "self": 316.73039412598814 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.09630047700011346, "count": 1, "self": 0.0014672840002276644, "children": { "RLTrainer._checkpoint": { "total": 0.0948331929998858, "count": 1, "self": 0.0948331929998858 } } } } } } }