{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3410817086696625, "min": 0.34023937582969666, "max": 1.47316575050354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10254.2802734375, "min": 10185.40625, "max": 44689.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29931.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29931.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6495689153671265, "min": -0.1056307703256607, "max": 0.6508188247680664, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.52886962890625, "min": -25.35138511657715, "max": 184.83255004882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0010810631792992353, "min": -0.008225778117775917, "max": 0.49512872099876404, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.3037787675857544, "min": -2.336121082305908, "max": 117.34550476074219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06575939865918674, "min": 0.06575939865918674, "max": 0.07441798879807315, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9206315812286143, "min": 0.5209259215865121, "max": 1.0442729147616774, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0160100356144886, "min": 0.0005157705674715772, "max": 0.0160100356144886, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2241404986028404, "min": 0.00567347624218735, "max": 0.2346591379949435, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.0182983168564294e-05, "min": 1.0182983168564294e-05, "max": 0.0003935341730450286, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00014256176435990011, "min": 0.00014256176435990011, "max": 0.004678856630285901, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254572142857142, "min": 0.10254572142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356400999999999, "min": 1.3886848, "max": 2.5697141, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026431757071428597, "min": 0.00026431757071428597, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037004459900000035, "min": 0.0037004459900000035, "max": 0.11699443859, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013475646264851093, "min": 0.013475646264851093, "max": 0.4892297387123108, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18865904211997986, "min": 0.18865904211997986, "max": 3.4246082305908203, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.19607843137254, "min": 288.19607843137254, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29396.0, "min": 16858.0, "max": 32915.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6918601758271745, "min": -0.9999500522390008, "max": 1.706809981316328, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.26159811019897, "min": -31.998401671648026, "max": 174.26159811019897, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6918601758271745, "min": -0.9999500522390008, "max": 1.706809981316328, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.26159811019897, "min": -31.998401671648026, "max": 174.26159811019897, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04020051931390466, "min": 0.04020051931390466, "max": 9.45686684285893, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.1406534893321805, "min": 4.064705326090916, "max": 160.76673632860184, "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": "1681979319", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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", "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": "1681982783" }, "total": 3463.943395468, "count": 1, "self": 0.5973215210001399, "children": { "run_training.setup": { "total": 0.14047379500016177, "count": 1, "self": 0.14047379500016177 }, "TrainerController.start_learning": { "total": 3463.2056001519995, "count": 1, "self": 2.424343712962127, "children": { "TrainerController._reset_env": { "total": 1.1377898390001064, "count": 1, "self": 1.1377898390001064 }, "TrainerController.advance": { "total": 3459.5216198160374, "count": 63869, "self": 2.6314636320348654, "children": { "env_step": { "total": 2311.939881856025, "count": 63869, "self": 2168.8915267690672, "children": { "SubprocessEnvManager._take_step": { "total": 141.58296216402277, "count": 63869, "self": 7.445506512946849, "children": { "TorchPolicy.evaluate": { "total": 134.13745565107592, "count": 62576, "self": 134.13745565107592 } } }, "workers": { "total": 1.465392922934825, "count": 63869, "self": 0.0, "children": { "worker_root": { "total": 3455.9085463850847, "count": 63869, "is_parallel": true, "self": 1461.038977868101, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029145660000722273, "count": 1, "is_parallel": true, "self": 0.0009469569999964733, "children": { "_process_rank_one_or_two_observation": { "total": 0.001967609000075754, "count": 8, "is_parallel": true, "self": 0.001967609000075754 } } }, "UnityEnvironment.step": { "total": 0.10886822900010884, "count": 1, "is_parallel": true, "self": 0.0006587930001842324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006102540000938461, "count": 1, "is_parallel": true, "self": 0.0006102540000938461 }, "communicator.exchange": { "total": 0.10560317999988911, "count": 1, "is_parallel": true, "self": 0.10560317999988911 }, "steps_from_proto": { "total": 0.0019960019999416545, "count": 1, "is_parallel": true, "self": 0.0004846179999731248, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015113839999685297, "count": 8, "is_parallel": true, "self": 0.0015113839999685297 } } } } } } }, "UnityEnvironment.step": { "total": 1994.8695685169837, "count": 63868, "is_parallel": true, "self": 45.98950803900834, "children": { "UnityEnvironment._generate_step_input": { "total": 27.437251301027118, "count": 63868, "is_parallel": true, "self": 27.437251301027118 }, "communicator.exchange": { "total": 1788.7070102210332, "count": 63868, "is_parallel": true, "self": 1788.7070102210332 }, "steps_from_proto": { "total": 132.73579895591502, "count": 63868, "is_parallel": true, "self": 29.902705926916497, "children": { "_process_rank_one_or_two_observation": { "total": 102.83309302899852, "count": 510944, "is_parallel": true, "self": 102.83309302899852 } } } } } } } } } } }, "trainer_advance": { "total": 1144.9502743279777, "count": 63869, "self": 4.63729208108316, "children": { "process_trajectory": { "total": 149.0316192759028, "count": 63869, "self": 148.79804945590286, "children": { "RLTrainer._checkpoint": { "total": 0.23356981999995696, "count": 2, "self": 0.23356981999995696 } } }, "_update_policy": { "total": 991.2813629709917, "count": 452, "self": 414.166394952892, "children": { "TorchPPOOptimizer.update": { "total": 577.1149680180997, "count": 22806, "self": 577.1149680180997 } } } } } } }, "trainer_threads": { "total": 1.1579995771171525e-06, "count": 1, "self": 1.1579995771171525e-06 }, "TrainerController._save_models": { "total": 0.12184562600032223, "count": 1, "self": 0.001737318000778032, "children": { "RLTrainer._checkpoint": { "total": 0.1201083079995442, "count": 1, "self": 0.1201083079995442 } } } } } } }