{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4318184554576874, "min": 0.42981794476509094, "max": 1.4064582586288452, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13023.64453125, "min": 12860.1533203125, "max": 42666.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29893.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29893.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45148518681526184, "min": -0.09664659202098846, "max": 0.45148518681526184, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.9010009765625, "min": -23.291828155517578, "max": 121.9010009765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006604312919080257, "min": -0.006604312919080257, "max": 0.5569151043891907, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.7831645011901855, "min": -1.7831645011901855, "max": 131.98887634277344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06452749765235787, "min": 0.06390087997294035, "max": 0.07434460007962548, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9033849671330101, "min": 0.5829702949627407, "max": 1.0475591947609908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014454873189672826, "min": 0.0004482599619023685, "max": 0.01578101315507887, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20236822465541957, "min": 0.005827379504730791, "max": 0.2209341841711042, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.757197414299997e-06, "min": 7.757197414299997e-06, "max": 0.0002948466392177875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010860076380019995, "min": 0.00010860076380019995, "max": 0.0033735922754693, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258569999999999, "min": 0.10258569999999999, "max": 0.1982822125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361997999999998, "min": 1.4361997999999998, "max": 2.4860812, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026831142999999994, "min": 0.00026831142999999994, "max": 0.00982839302875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003756360019999999, "min": 0.003756360019999999, "max": 0.11247061693, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01677914522588253, "min": 0.01677914522588253, "max": 0.6100777983665466, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23490804433822632, "min": 0.23490804433822632, "max": 4.880622386932373, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 423.81333333333333, "min": 423.81333333333333, "max": 998.8333333333334, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31786.0, "min": 16308.0, "max": 32909.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4675394564278816, "min": -0.9364938016515225, "max": 1.4675394564278816, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.532998688519, "min": -29.96780165284872, "max": 111.532998688519, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4675394564278816, "min": -0.9364938016515225, "max": 1.4675394564278816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.532998688519, "min": -29.96780165284872, "max": 111.532998688519, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07426877349222961, "min": 0.07426877349222961, "max": 13.635930163895383, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.6444267854094505, "min": 5.151852304436034, "max": 231.8108127862215, "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": "1767200163", "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": "1767202346" }, "total": 2183.1484350899996, "count": 1, "self": 0.47953076799967675, "children": { "run_training.setup": { "total": 0.022512744000323437, "count": 1, "self": 0.022512744000323437 }, "TrainerController.start_learning": { "total": 2182.6463915779996, "count": 1, "self": 1.3367634760074907, "children": { "TrainerController._reset_env": { "total": 1.9966116330001569, "count": 1, "self": 1.9966116330001569 }, "TrainerController.advance": { "total": 2179.2293578019926, "count": 63493, "self": 1.3120025739904122, "children": { "env_step": { "total": 1527.2178746880354, "count": 63493, "self": 1377.9147828009213, "children": { "SubprocessEnvManager._take_step": { "total": 148.50891760601417, "count": 63493, "self": 4.562585600940565, "children": { "TorchPolicy.evaluate": { "total": 143.9463320050736, "count": 62550, "self": 143.9463320050736 } } }, "workers": { "total": 0.7941742810999131, "count": 63493, "self": 0.0, "children": { "worker_root": { "total": 2175.7144722040093, "count": 63493, "is_parallel": true, "self": 915.1492270000267, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019054300000789226, "count": 1, "is_parallel": true, "self": 0.0006490549999398354, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012563750001390872, "count": 8, "is_parallel": true, "self": 0.0012563750001390872 } } }, "UnityEnvironment.step": { "total": 0.0475384659998781, "count": 1, "is_parallel": true, "self": 0.0005267939995974302, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004571350000333041, "count": 1, "is_parallel": true, "self": 0.0004571350000333041 }, "communicator.exchange": { "total": 0.04488604500011206, "count": 1, "is_parallel": true, "self": 0.04488604500011206 }, "steps_from_proto": { "total": 0.001668492000135302, "count": 1, "is_parallel": true, "self": 0.0003647599996838835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013037320004514186, "count": 8, "is_parallel": true, "self": 0.0013037320004514186 } } } } } } }, "UnityEnvironment.step": { "total": 1260.5652452039826, "count": 63492, "is_parallel": true, "self": 33.835818236921114, "children": { "UnityEnvironment._generate_step_input": { "total": 23.732183649139188, "count": 63492, "is_parallel": true, "self": 23.732183649139188 }, "communicator.exchange": { "total": 1095.2672702549853, "count": 63492, "is_parallel": true, "self": 1095.2672702549853 }, "steps_from_proto": { "total": 107.729973062937, "count": 63492, "is_parallel": true, "self": 22.292867057084095, "children": { "_process_rank_one_or_two_observation": { "total": 85.43710600585291, "count": 507936, "is_parallel": true, "self": 85.43710600585291 } } } } } } } } } } }, "trainer_advance": { "total": 650.6994805399668, "count": 63493, "self": 2.60663470092004, "children": { "process_trajectory": { "total": 123.05150918605796, "count": 63493, "self": 122.85742944705771, "children": { "RLTrainer._checkpoint": { "total": 0.19407973900024444, "count": 2, "self": 0.19407973900024444 } } }, "_update_policy": { "total": 525.0413366529888, "count": 451, "self": 292.86069302498845, "children": { "TorchPPOOptimizer.update": { "total": 232.18064362800033, "count": 22755, "self": 232.18064362800033 } } } } } } }, "trainer_threads": { "total": 1.0260000635753386e-06, "count": 1, "self": 1.0260000635753386e-06 }, "TrainerController._save_models": { "total": 0.0836576409992631, "count": 1, "self": 0.0009589749988663243, "children": { "RLTrainer._checkpoint": { "total": 0.08269866600039677, "count": 1, "self": 0.08269866600039677 } } } } } } }