{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4795747399330139, "min": 0.4795747399330139, "max": 1.4618937969207764, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14563.7255859375, "min": 14563.7255859375, "max": 44348.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5876201391220093, "min": -0.16776585578918457, "max": 0.5876201391220093, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.77078247070312, "min": -39.7605094909668, "max": 162.77078247070312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.26975661516189575, "min": -0.013640335761010647, "max": 0.3809826076030731, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 74.72257995605469, "min": -3.601048707962036, "max": 90.29287719726562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06357700541460266, "min": 0.06357700541460266, "max": 0.07324024395895355, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9536550812190399, "min": 0.5061449119265876, "max": 1.0696497061957524, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017984554277629485, "min": 0.00032887019811460023, "max": 0.017984554277629485, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2697683141644423, "min": 0.003946442377375203, "max": 0.2697683141644423, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4614375128866656e-06, "min": 7.4614375128866656e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011192156269329998, "min": 0.00011192156269329998, "max": 0.0036354898881700995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248711333333335, "min": 0.10248711333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373067000000002, "min": 1.3886848, "max": 2.6118299, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258462622, "min": 0.000258462622, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038769393300000002, "min": 0.0038769393300000002, "max": 0.12120180700999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008419668301939964, "min": 0.00836948398500681, "max": 0.46496105194091797, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1262950301170349, "min": 0.11717277765274048, "max": 3.254727363586426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.13793103448273, "min": 329.13793103448273, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28635.0, "min": 15984.0, "max": 33059.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6278772479431196, "min": -1.0000000521540642, "max": 1.6278772479431196, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.25319781899452, "min": -31.995601668953896, "max": 151.10519791394472, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6278772479431196, "min": -1.0000000521540642, "max": 1.6278772479431196, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.25319781899452, "min": -31.995601668953896, "max": 151.10519791394472, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02871607588828986, "min": 0.02871607588828986, "max": 9.456846978515387, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5270146781695075, "min": 2.5270146781695075, "max": 151.30955165624619, "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": "1692597425", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 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": "1692599689" }, "total": 2264.182567473, "count": 1, "self": 0.487614270999984, "children": { "run_training.setup": { "total": 0.043287183999950685, "count": 1, "self": 0.043287183999950685 }, "TrainerController.start_learning": { "total": 2263.651666018, "count": 1, "self": 1.39233449898029, "children": { "TrainerController._reset_env": { "total": 4.53210393400002, "count": 1, "self": 4.53210393400002 }, "TrainerController.advance": { "total": 2257.6228395030193, "count": 63814, "self": 1.411756680057806, "children": { "env_step": { "total": 1597.6274045459904, "count": 63814, "self": 1486.2651131489697, "children": { "SubprocessEnvManager._take_step": { "total": 110.49027684602186, "count": 63814, "self": 4.823317127010455, "children": { "TorchPolicy.evaluate": { "total": 105.6669597190114, "count": 62562, "self": 105.6669597190114 } } }, "workers": { "total": 0.8720145509988697, "count": 63814, "self": 0.0, "children": { "worker_root": { "total": 2258.643598209958, "count": 63814, "is_parallel": true, "self": 889.9842033819823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053855469999462, "count": 1, "is_parallel": true, "self": 0.003914586000064446, "children": { "_process_rank_one_or_two_observation": { "total": 0.001470960999881754, "count": 8, "is_parallel": true, "self": 0.001470960999881754 } } }, "UnityEnvironment.step": { "total": 0.04880758199999491, "count": 1, "is_parallel": true, "self": 0.000603139999952873, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004745170000433063, "count": 1, "is_parallel": true, "self": 0.0004745170000433063 }, "communicator.exchange": { "total": 0.04573494999999639, "count": 1, "is_parallel": true, "self": 0.04573494999999639 }, "steps_from_proto": { "total": 0.0019949750000023414, "count": 1, "is_parallel": true, "self": 0.00037864500018258695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016163299998197544, "count": 8, "is_parallel": true, "self": 0.0016163299998197544 } } } } } } }, "UnityEnvironment.step": { "total": 1368.6593948279756, "count": 63813, "is_parallel": true, "self": 35.28641713501315, "children": { "UnityEnvironment._generate_step_input": { "total": 23.38670791600657, "count": 63813, "is_parallel": true, "self": 23.38670791600657 }, "communicator.exchange": { "total": 1200.7392607100014, "count": 63813, "is_parallel": true, "self": 1200.7392607100014 }, "steps_from_proto": { "total": 109.24700906695443, "count": 63813, "is_parallel": true, "self": 21.26820899389429, "children": { "_process_rank_one_or_two_observation": { "total": 87.97880007306014, "count": 510504, "is_parallel": true, "self": 87.97880007306014 } } } } } } } } } } }, "trainer_advance": { "total": 658.5836782769711, "count": 63814, "self": 2.6859923669653654, "children": { "process_trajectory": { "total": 112.6829998620077, "count": 63814, "self": 112.47036019200766, "children": { "RLTrainer._checkpoint": { "total": 0.21263967000004413, "count": 2, "self": 0.21263967000004413 } } }, "_update_policy": { "total": 543.214686047998, "count": 454, "self": 354.2356010110324, "children": { "TorchPPOOptimizer.update": { "total": 188.97908503696567, "count": 22749, "self": 188.97908503696567 } } } } } } }, "trainer_threads": { "total": 1.3030003174208105e-06, "count": 1, "self": 1.3030003174208105e-06 }, "TrainerController._save_models": { "total": 0.10438677899992399, "count": 1, "self": 0.0013426810000964906, "children": { "RLTrainer._checkpoint": { "total": 0.1030440979998275, "count": 1, "self": 0.1030440979998275 } } } } } } }