{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6478382349014282, "min": 0.6478382349014282, "max": 1.501163363456726, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 19414.416015625, "min": 19414.416015625, "max": 45539.29296875, "count": 20 }, "Pyramids.Step.mean": { "value": 599938.0, "min": 29952.0, "max": 599938.0, "count": 20 }, "Pyramids.Step.sum": { "value": 599938.0, "min": 29952.0, "max": 599938.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18724876642227173, "min": -0.18214330077171326, "max": 0.18724876642227173, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 47.561187744140625, "min": -43.16796112060547, "max": 47.561187744140625, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005261237267404795, "min": 0.005261237267404795, "max": 0.3343900442123413, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3363542556762695, "min": 1.3363542556762695, "max": 79.25044250488281, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06920473634541155, "min": 0.06683283463617834, "max": 0.07195383903981176, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9688663088357617, "min": 0.47693756886074806, "max": 1.0728707710659366, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011946729921744139, "min": 0.0008682443716028568, "max": 0.011946729921744139, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16725421890441794, "min": 0.0060777106012199975, "max": 0.16725421890441794, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.054847648416671e-06, "min": 7.054847648416671e-06, "max": 0.0002919177169798095, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 9.876786707783339e-05, "min": 9.876786707783339e-05, "max": 0.003045879384707, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10235158333333332, "min": 0.10235158333333332, "max": 0.1973059047619048, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4329221666666665, "min": 1.3485226666666668, "max": 2.4152929999999997, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.00024492317500000003, "min": 0.00024492317500000003, "max": 0.009730859885714286, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034289244500000007, "min": 0.0034289244500000007, "max": 0.10156777070000002, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016863195225596428, "min": 0.016720183193683624, "max": 0.3915402889251709, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2360847443342209, "min": 0.2360847443342209, "max": 2.7407820224761963, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 587.530612244898, "min": 587.530612244898, "max": 999.0, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28789.0, "min": 15984.0, "max": 32936.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0041754768819224, "min": -1.0000000521540642, "max": 1.0041754768819224, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 49.2045983672142, "min": -32.000001668930054, "max": 49.2045983672142, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0041754768819224, "min": -1.0000000521540642, "max": 1.0041754768819224, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 49.2045983672142, "min": -32.000001668930054, "max": 49.2045983672142, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1021522772094539, "min": 0.1021522772094539, "max": 7.710925901308656, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 5.005461583263241, "min": 5.005461583263241, "max": 123.37481442093849, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714050857", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714052892" }, "total": 2035.5195693849998, "count": 1, "self": 1.170947453999588, "children": { "run_training.setup": { "total": 0.0873782520000077, "count": 1, "self": 0.0873782520000077 }, "TrainerController.start_learning": { "total": 2034.2612436790002, "count": 1, "self": 1.4362915860294834, "children": { "TrainerController._reset_env": { "total": 2.5098585850000745, "count": 1, "self": 2.5098585850000745 }, "TrainerController.advance": { "total": 2030.1492163069706, "count": 37937, "self": 1.71343659389413, "children": { "env_step": { "total": 1311.7210331760184, "count": 37937, "self": 1202.3931517710591, "children": { "SubprocessEnvManager._take_step": { "total": 108.37235794696221, "count": 37937, "self": 5.114811040994255, "children": { "TorchPolicy.evaluate": { "total": 103.25754690596796, "count": 37559, "self": 103.25754690596796 } } }, "workers": { "total": 0.9555234579970602, "count": 37937, "self": 0.0, "children": { "worker_root": { "total": 2029.6379632149115, "count": 37937, "is_parallel": true, "self": 951.950502307945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022997490000307153, "count": 1, "is_parallel": true, "self": 0.0006597380001949205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016400109998357948, "count": 8, "is_parallel": true, "self": 0.0016400109998357948 } } }, "UnityEnvironment.step": { "total": 0.06654963899995892, "count": 1, "is_parallel": true, "self": 0.0008212950001507124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006649509998624126, "count": 1, "is_parallel": true, "self": 0.0006649509998624126 }, "communicator.exchange": { "total": 0.0628841889999876, "count": 1, "is_parallel": true, "self": 0.0628841889999876 }, "steps_from_proto": { "total": 0.0021792039999581903, "count": 1, "is_parallel": true, "self": 0.000498880999884932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016803230000732583, "count": 8, "is_parallel": true, "self": 0.0016803230000732583 } } } } } } }, "UnityEnvironment.step": { "total": 1077.6874609069664, "count": 37936, "is_parallel": true, "self": 32.51179417788785, "children": { "UnityEnvironment._generate_step_input": { "total": 17.66922213103976, "count": 37936, "is_parallel": true, "self": 17.66922213103976 }, "communicator.exchange": { "total": 944.2755419109951, "count": 37936, "is_parallel": true, "self": 944.2755419109951 }, "steps_from_proto": { "total": 83.23090268704368, "count": 37936, "is_parallel": true, "self": 17.833601884062773, "children": { "_process_rank_one_or_two_observation": { "total": 65.39730080298091, "count": 303488, "is_parallel": true, "self": 65.39730080298091 } } } } } } } } } } }, "trainer_advance": { "total": 716.7147465370581, "count": 37937, "self": 2.7046983360226022, "children": { "process_trajectory": { "total": 110.84748384203613, "count": 37937, "self": 110.71504253303647, "children": { "RLTrainer._checkpoint": { "total": 0.13244130899965967, "count": 1, "self": 0.13244130899965967 } } }, "_update_policy": { "total": 603.1625643589994, "count": 258, "self": 239.17001531900723, "children": { "TorchPPOOptimizer.update": { "total": 363.9925490399921, "count": 13689, "self": 363.9925490399921 } } } } } } }, "trainer_threads": { "total": 1.4830002328380942e-06, "count": 1, "self": 1.4830002328380942e-06 }, "TrainerController._save_models": { "total": 0.1658757179998247, "count": 1, "self": 0.005956058999800007, "children": { "RLTrainer._checkpoint": { "total": 0.1599196590000247, "count": 1, "self": 0.1599196590000247 } } } } } } }