{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4630821645259857, "min": 0.4449754059314728, "max": 1.4241944551467896, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13929.51171875, "min": 13363.5009765625, "max": 43204.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29984.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29984.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45861712098121643, "min": -0.11178482323884964, "max": 0.48593631386756897, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.45076751708984, "min": -26.828357696533203, "max": 132.66061401367188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022885648533701897, "min": -0.03231687471270561, "max": 0.4256077706813812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.110467910766602, "min": -8.143852233886719, "max": 101.29464721679688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06653981398336502, "min": 0.06403459008323527, "max": 0.07266814800079438, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9315573957671102, "min": 0.5570226457893805, "max": 1.0547737967572175, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013986490499519277, "min": 0.00011095229723620667, "max": 0.014451769975203818, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19581086699326988, "min": 0.0014423798640706867, "max": 0.205165641662247, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.416226099385714e-06, "min": 7.416226099385714e-06, "max": 0.0002948508017164, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038271653914, "min": 0.0001038271653914, "max": 0.0035070938309687996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247204285714284, "min": 0.10247204285714284, "max": 0.1982836, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346085999999998, "min": 1.4346085999999998, "max": 2.5690312000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025695708142857145, "min": 0.00025695708142857145, "max": 0.00982853164, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359739914, "min": 0.00359739914, "max": 0.11692621688000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011457763612270355, "min": 0.011457763612270355, "max": 0.46690621972084045, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16040869057178497, "min": 0.16040869057178497, "max": 3.7352497577667236, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 397.61538461538464, "min": 364.53846153846155, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31014.0, "min": 16399.0, "max": 32595.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4228358718638237, "min": -0.9999467191596826, "max": 1.5599063081266005, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 110.98119800537825, "min": -31.995601668953896, "max": 123.23259834200144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4228358718638237, "min": -0.9999467191596826, "max": 1.5599063081266005, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 110.98119800537825, "min": -31.995601668953896, "max": 123.23259834200144, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04722479881363539, "min": 0.045106792224562264, "max": 9.69014005801257, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6835343074635603, "min": 3.563436585740419, "max": 164.73238098621368, "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": "1708043229", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708045431" }, "total": 2202.5841689069994, "count": 1, "self": 0.5311004349996438, "children": { "run_training.setup": { "total": 0.04493276599987439, "count": 1, "self": 0.04493276599987439 }, "TrainerController.start_learning": { "total": 2202.008135706, "count": 1, "self": 1.340281121983935, "children": { "TrainerController._reset_env": { "total": 2.448347540999748, "count": 1, "self": 2.448347540999748 }, "TrainerController.advance": { "total": 2198.1249183000164, "count": 63598, "self": 1.5376492427667472, "children": { "env_step": { "total": 1568.6628836021537, "count": 63598, "self": 1436.737800378025, "children": { "SubprocessEnvManager._take_step": { "total": 131.0438932149791, "count": 63598, "self": 4.899333277910046, "children": { "TorchPolicy.evaluate": { "total": 126.14455993706906, "count": 62557, "self": 126.14455993706906 } } }, "workers": { "total": 0.8811900091495772, "count": 63598, "self": 0.0, "children": { "worker_root": { "total": 2196.5665968208696, "count": 63598, "is_parallel": true, "self": 877.7200548708579, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021645189999617287, "count": 1, "is_parallel": true, "self": 0.0006774930016035796, "children": { "_process_rank_one_or_two_observation": { "total": 0.001487025998358149, "count": 8, "is_parallel": true, "self": 0.001487025998358149 } } }, "UnityEnvironment.step": { "total": 0.048102089000167325, "count": 1, "is_parallel": true, "self": 0.0005663790007019998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004766409992953413, "count": 1, "is_parallel": true, "self": 0.0004766409992953413 }, "communicator.exchange": { "total": 0.045416153000587656, "count": 1, "is_parallel": true, "self": 0.045416153000587656 }, "steps_from_proto": { "total": 0.0016429159995823284, "count": 1, "is_parallel": true, "self": 0.00035210000078222947, "children": { "_process_rank_one_or_two_observation": { "total": 0.001290815998800099, "count": 8, "is_parallel": true, "self": 0.001290815998800099 } } } } } } }, "UnityEnvironment.step": { "total": 1318.8465419500117, "count": 63597, "is_parallel": true, "self": 35.06795853771473, "children": { "UnityEnvironment._generate_step_input": { "total": 24.84871911508253, "count": 63597, "is_parallel": true, "self": 24.84871911508253 }, "communicator.exchange": { "total": 1160.0065789049868, "count": 63597, "is_parallel": true, "self": 1160.0065789049868 }, "steps_from_proto": { "total": 98.92328539222763, "count": 63597, "is_parallel": true, "self": 19.6580982419473, "children": { "_process_rank_one_or_two_observation": { "total": 79.26518715028033, "count": 508776, "is_parallel": true, "self": 79.26518715028033 } } } } } } } } } } }, "trainer_advance": { "total": 627.924385455096, "count": 63598, "self": 2.710339611176096, "children": { "process_trajectory": { "total": 125.8383804749219, "count": 63598, "self": 125.59499526292257, "children": { "RLTrainer._checkpoint": { "total": 0.24338521199933894, "count": 2, "self": 0.24338521199933894 } } }, "_update_policy": { "total": 499.37566536899794, "count": 452, "self": 294.8808876969788, "children": { "TorchPPOOptimizer.update": { "total": 204.49477767201915, "count": 22791, "self": 204.49477767201915 } } } } } } }, "trainer_threads": { "total": 1.5810001059435308e-06, "count": 1, "self": 1.5810001059435308e-06 }, "TrainerController._save_models": { "total": 0.09458716199969786, "count": 1, "self": 0.00149247299941635, "children": { "RLTrainer._checkpoint": { "total": 0.0930946890002815, "count": 1, "self": 0.0930946890002815 } } } } } } }