{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4488804340362549, "min": 0.44318872690200806, "max": 1.4866716861724854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13545.416015625, "min": 13402.02734375, "max": 45099.671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4849868714809418, "min": -0.13220243155956268, "max": 0.4849868714809418, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.9164276123047, "min": -31.33197784423828, "max": 131.9164276123047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025886062532663345, "min": 0.0008639831794425845, "max": 0.24651314318180084, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.041008949279785, "min": 0.21945172548294067, "max": 58.423614501953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06497095891577344, "min": 0.06497095891577344, "max": 0.07411337350141348, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9745643837366016, "min": 0.4743345345928462, "max": 1.1117006025212022, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012470686275970793, "min": 0.0011128911273413824, "max": 0.014562932951923496, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1870602941395619, "min": 0.0077902378913896776, "max": 0.20388106132692893, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.522517492526668e-06, "min": 7.522517492526668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011283776238790002, "min": 0.00011283776238790002, "max": 0.0036331468889510997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250747333333333, "min": 0.10250747333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376121, "min": 1.3691136000000002, "max": 2.6110489, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002604965860000001, "min": 0.0002604965860000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003907448790000001, "min": 0.003907448790000001, "max": 0.12112378510999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008407405577600002, "min": 0.008221850730478764, "max": 0.3840178847312927, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12611109018325806, "min": 0.11510591208934784, "max": 2.6881251335144043, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.0933333333333, "min": 388.89473684210526, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31807.0, "min": 15984.0, "max": 33847.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4425306423505146, "min": -1.0000000521540642, "max": 1.5321341855941635, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.1897981762886, "min": -32.000001668930054, "max": 116.44219810515642, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4425306423505146, "min": -1.0000000521540642, "max": 1.5321341855941635, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.1897981762886, "min": -32.000001668930054, "max": 116.44219810515642, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03680487084493507, "min": 0.03337584943277761, "max": 8.22837283834815, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.76036531337013, "min": 2.503188707458321, "max": 131.6539654135704, "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": "1707816160", "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 Training --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": "1707818304" }, "total": 2143.483272429, "count": 1, "self": 0.4879520700001194, "children": { "run_training.setup": { "total": 0.058414658999936364, "count": 1, "self": 0.058414658999936364 }, "TrainerController.start_learning": { "total": 2142.9369057, "count": 1, "self": 1.4291691921716847, "children": { "TrainerController._reset_env": { "total": 2.3512748289999763, "count": 1, "self": 2.3512748289999763 }, "TrainerController.advance": { "total": 2139.0693769358277, "count": 63702, "self": 1.4630600048308224, "children": { "env_step": { "total": 1515.970830760029, "count": 63702, "self": 1383.7385666900027, "children": { "SubprocessEnvManager._take_step": { "total": 131.38991806806416, "count": 63702, "self": 4.773405020031078, "children": { "TorchPolicy.evaluate": { "total": 126.61651304803308, "count": 62557, "self": 126.61651304803308 } } }, "workers": { "total": 0.8423460019621416, "count": 63702, "self": 0.0, "children": { "worker_root": { "total": 2137.9072583590178, "count": 63702, "is_parallel": true, "self": 869.6254016660309, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021145179998711683, "count": 1, "is_parallel": true, "self": 0.0006990370002313284, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014154809996398399, "count": 8, "is_parallel": true, "self": 0.0014154809996398399 } } }, "UnityEnvironment.step": { "total": 0.05261178899991137, "count": 1, "is_parallel": true, "self": 0.0006011229997966439, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005417639999905077, "count": 1, "is_parallel": true, "self": 0.0005417639999905077 }, "communicator.exchange": { "total": 0.0495431260001169, "count": 1, "is_parallel": true, "self": 0.0495431260001169 }, "steps_from_proto": { "total": 0.0019257760000073176, "count": 1, "is_parallel": true, "self": 0.0004324609999457607, "children": { "_process_rank_one_or_two_observation": { "total": 0.001493315000061557, "count": 8, "is_parallel": true, "self": 0.001493315000061557 } } } } } } }, "UnityEnvironment.step": { "total": 1268.2818566929868, "count": 63701, "is_parallel": true, "self": 34.72844787590702, "children": { "UnityEnvironment._generate_step_input": { "total": 25.76309535509381, "count": 63701, "is_parallel": true, "self": 25.76309535509381 }, "communicator.exchange": { "total": 1105.019764163976, "count": 63701, "is_parallel": true, "self": 1105.019764163976 }, "steps_from_proto": { "total": 102.77054929800988, "count": 63701, "is_parallel": true, "self": 20.731569220983147, "children": { "_process_rank_one_or_two_observation": { "total": 82.03898007702674, "count": 509608, "is_parallel": true, "self": 82.03898007702674 } } } } } } } } } } }, "trainer_advance": { "total": 621.6354861709679, "count": 63702, "self": 2.6164761209611243, "children": { "process_trajectory": { "total": 127.21050682300393, "count": 63702, "self": 127.01537612400443, "children": { "RLTrainer._checkpoint": { "total": 0.19513069899949187, "count": 2, "self": 0.19513069899949187 } } }, "_update_policy": { "total": 491.8085032270028, "count": 446, "self": 289.92323996703453, "children": { "TorchPPOOptimizer.update": { "total": 201.88526325996827, "count": 22782, "self": 201.88526325996827 } } } } } } }, "trainer_threads": { "total": 1.0310004654456861e-06, "count": 1, "self": 1.0310004654456861e-06 }, "TrainerController._save_models": { "total": 0.08708371200009424, "count": 1, "self": 0.0014753400000699912, "children": { "RLTrainer._checkpoint": { "total": 0.08560837200002425, "count": 1, "self": 0.08560837200002425 } } } } } } }