{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49505943059921265, "min": 0.48245206475257874, "max": 1.4501056671142578, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14828.0205078125, "min": 14419.52734375, "max": 43990.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29891.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29891.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5566858649253845, "min": -0.10187146067619324, "max": 0.5917426943778992, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.98541259765625, "min": -24.44915008544922, "max": 166.27969360351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0032439702190458775, "min": -0.007153721060603857, "max": 0.2887189984321594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.9147995710372925, "min": -1.938658356666565, "max": 69.5812759399414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06740343718584406, "min": 0.06404614024601567, "max": 0.07147230604831648, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9436481206018168, "min": 0.49355955546468916, "max": 1.0720845907247472, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016820526379714946, "min": 0.0005921400686570875, "max": 0.016820526379714946, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23548736931600922, "min": 0.006513540755227963, "max": 0.23548736931600922, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.657340304728566e-06, "min": 7.657340304728566e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010720276426619994, "min": 0.00010720276426619994, "max": 0.0036332155889281996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255241428571427, "min": 0.10255241428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357337999999997, "min": 1.3886848, "max": 2.6110718, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002649861871428571, "min": 0.0002649861871428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037098066199999988, "min": 0.0037098066199999988, "max": 0.12112607282000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010643445886671543, "min": 0.010643445886671543, "max": 0.44882455468177795, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14900824427604675, "min": 0.14900824427604675, "max": 3.1417717933654785, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.9120879120879, "min": 323.44329896907215, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31478.0, "min": 16818.0, "max": 32262.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5856599818501207, "min": -0.9999750521965325, "max": 1.6559278216097773, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.70939836651087, "min": -31.99920167028904, "max": 160.6249986961484, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5856599818501207, "min": -0.9999750521965325, "max": 1.6559278216097773, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.70939836651087, "min": -31.99920167028904, "max": 160.6249986961484, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03842931199356422, "min": 0.03741378383470949, "max": 8.693341975702959, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.45863807942078, "min": 3.2677668145333882, "max": 147.7868135869503, "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": "1767315155", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767317371" }, "total": 2216.470467614, "count": 1, "self": 0.48084673700032, "children": { "run_training.setup": { "total": 0.02246302799994737, "count": 1, "self": 0.02246302799994737 }, "TrainerController.start_learning": { "total": 2215.9671578489997, "count": 1, "self": 1.2928799810406417, "children": { "TrainerController._reset_env": { "total": 2.00360935599997, "count": 1, "self": 2.00360935599997 }, "TrainerController.advance": { "total": 2212.5946752489594, "count": 63881, "self": 1.4217386709256061, "children": { "env_step": { "total": 1556.819373405994, "count": 63881, "self": 1409.2339560910673, "children": { "SubprocessEnvManager._take_step": { "total": 146.8012373149702, "count": 63881, "self": 4.489756867935057, "children": { "TorchPolicy.evaluate": { "total": 142.31148044703514, "count": 62569, "self": 142.31148044703514 } } }, "workers": { "total": 0.78417999995645, "count": 63881, "self": 0.0, "children": { "worker_root": { "total": 2209.4644759969297, "count": 63881, "is_parallel": true, "self": 914.7265561389449, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017399539999587432, "count": 1, "is_parallel": true, "self": 0.0005207720005273586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012191819994313846, "count": 8, "is_parallel": true, "self": 0.0012191819994313846 } } }, "UnityEnvironment.step": { "total": 0.04779561600003035, "count": 1, "is_parallel": true, "self": 0.0005645569999614963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005000690000542818, "count": 1, "is_parallel": true, "self": 0.0005000690000542818 }, "communicator.exchange": { "total": 0.04503734800005077, "count": 1, "is_parallel": true, "self": 0.04503734800005077 }, "steps_from_proto": { "total": 0.001693641999963802, "count": 1, "is_parallel": true, "self": 0.0004042000000481494, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012894419999156526, "count": 8, "is_parallel": true, "self": 0.0012894419999156526 } } } } } } }, "UnityEnvironment.step": { "total": 1294.7379198579847, "count": 63880, "is_parallel": true, "self": 33.30613286292373, "children": { "UnityEnvironment._generate_step_input": { "total": 23.027440874035165, "count": 63880, "is_parallel": true, "self": 23.027440874035165 }, "communicator.exchange": { "total": 1132.4390270409906, "count": 63880, "is_parallel": true, "self": 1132.4390270409906 }, "steps_from_proto": { "total": 105.96531908003521, "count": 63880, "is_parallel": true, "self": 22.010429951947117, "children": { "_process_rank_one_or_two_observation": { "total": 83.9548891280881, "count": 511040, "is_parallel": true, "self": 83.9548891280881 } } } } } } } } } } }, "trainer_advance": { "total": 654.3535631720401, "count": 63881, "self": 2.564678705007509, "children": { "process_trajectory": { "total": 123.35465102602961, "count": 63881, "self": 123.17939089902961, "children": { "RLTrainer._checkpoint": { "total": 0.17526012700000138, "count": 2, "self": 0.17526012700000138 } } }, "_update_policy": { "total": 528.434233441003, "count": 453, "self": 296.27119029895516, "children": { "TorchPPOOptimizer.update": { "total": 232.16304314204785, "count": 22782, "self": 232.16304314204785 } } } } } } }, "trainer_threads": { "total": 8.199999683711212e-07, "count": 1, "self": 8.199999683711212e-07 }, "TrainerController._save_models": { "total": 0.0759924429999046, "count": 1, "self": 0.001288004999878467, "children": { "RLTrainer._checkpoint": { "total": 0.07470443800002613, "count": 1, "self": 0.07470443800002613 } } } } } } }