{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5437203049659729, "min": 0.5437203049659729, "max": 1.464453935623169, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16363.806640625, "min": 16363.806640625, "max": 44425.67578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.059836070984601974, "min": -0.11125834286212921, "max": 0.13300727307796478, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 14.65983772277832, "min": -26.702001571655273, "max": 33.78384780883789, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017197515815496445, "min": 0.011928383260965347, "max": 0.18645647168159485, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.213391304016113, "min": 2.8866686820983887, "max": 45.122467041015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0649612658992174, "min": 0.0649612658992174, "max": 0.07289258630372723, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9094577225890437, "min": 0.5035401426271425, "max": 1.0367612372501753, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005639774115154847, "min": 5.662456823820444e-05, "max": 0.007726134443276221, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07895683761216786, "min": 0.0007361193870966577, "max": 0.10816588220586709, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.772990266178575e-06, "min": 7.772990266178575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010882186372650004, "min": 0.00010882186372650004, "max": 0.0033821810726064007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025909642857143, "min": 0.1025909642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362735000000002, "min": 1.3886848, "max": 2.5273936, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002688373321428573, "min": 0.0002688373321428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003763722650000002, "min": 0.003763722650000002, "max": 0.11276662064000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013598041608929634, "min": 0.013598041608929634, "max": 0.2780899405479431, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19037258625030518, "min": 0.19037258625030518, "max": 1.946629524230957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 814.4473684210526, "min": 699.1304347826087, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30949.0, "min": 15984.0, "max": 32692.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.10917293038722631, "min": -1.0000000521540642, "max": 0.5180651838688747, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 4.0393984243273735, "min": -31.998801678419113, "max": 23.830998457968235, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.10917293038722631, "min": -1.0000000521540642, "max": 0.5180651838688747, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 4.0393984243273735, "min": -31.998801678419113, "max": 23.830998457968235, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11583924325610939, "min": 0.1013466584054581, "max": 5.377204356249422, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.286052000476047, "min": 3.8402916701161303, "max": 86.03526969999075, "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": "1678803051", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1678806423" }, "total": 3371.956234458001, "count": 1, "self": 0.6476458200004345, "children": { "run_training.setup": { "total": 0.1382753750003758, "count": 1, "self": 0.1382753750003758 }, "TrainerController.start_learning": { "total": 3371.170313263, "count": 1, "self": 2.7054193488611418, "children": { "TrainerController._reset_env": { "total": 5.993590939999194, "count": 1, "self": 5.993590939999194 }, "TrainerController.advance": { "total": 3362.3656709161387, "count": 63138, "self": 2.6811576554491694, "children": { "env_step": { "total": 2149.37308282479, "count": 63138, "self": 1989.767124366811, "children": { "SubprocessEnvManager._take_step": { "total": 157.98456227011775, "count": 63138, "self": 7.881680239178422, "children": { "TorchPolicy.evaluate": { "total": 150.10288203093933, "count": 62582, "self": 150.10288203093933 } } }, "workers": { "total": 1.6213961878611372, "count": 63138, "self": 0.0, "children": { "worker_root": { "total": 3363.800554649838, "count": 63138, "is_parallel": true, "self": 1570.624672439746, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0038657850000163307, "count": 1, "is_parallel": true, "self": 0.0015071259995238506, "children": { "_process_rank_one_or_two_observation": { "total": 0.00235865900049248, "count": 8, "is_parallel": true, "self": 0.00235865900049248 } } }, "UnityEnvironment.step": { "total": 0.13784733299962681, "count": 1, "is_parallel": true, "self": 0.000709930999619246, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006727740001224447, "count": 1, "is_parallel": true, "self": 0.0006727740001224447 }, "communicator.exchange": { "total": 0.1340678950000438, "count": 1, "is_parallel": true, "self": 0.1340678950000438 }, "steps_from_proto": { "total": 0.0023967329998413334, "count": 1, "is_parallel": true, "self": 0.0007403109984807088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016564220013606246, "count": 8, "is_parallel": true, "self": 0.0016564220013606246 } } } } } } }, "UnityEnvironment.step": { "total": 1793.175882210092, "count": 63137, "is_parallel": true, "self": 46.623449161138524, "children": { "UnityEnvironment._generate_step_input": { "total": 28.117133666873997, "count": 63137, "is_parallel": true, "self": 28.117133666873997 }, "communicator.exchange": { "total": 1585.1152901359173, "count": 63137, "is_parallel": true, "self": 1585.1152901359173 }, "steps_from_proto": { "total": 133.32000924616204, "count": 63137, "is_parallel": true, "self": 30.636305833073493, "children": { "_process_rank_one_or_two_observation": { "total": 102.68370341308855, "count": 505096, "is_parallel": true, "self": 102.68370341308855 } } } } } } } } } } }, "trainer_advance": { "total": 1210.3114304358996, "count": 63138, "self": 5.165429273812151, "children": { "process_trajectory": { "total": 179.3964848161031, "count": 63138, "self": 179.16788736410217, "children": { "RLTrainer._checkpoint": { "total": 0.2285974520009404, "count": 2, "self": 0.2285974520009404 } } }, "_update_policy": { "total": 1025.7495163459844, "count": 443, "self": 417.4798575380455, "children": { "TorchPPOOptimizer.update": { "total": 608.2696588079389, "count": 22767, "self": 608.2696588079389 } } } } } } }, "trainer_threads": { "total": 1.191001501865685e-06, "count": 1, "self": 1.191001501865685e-06 }, "TrainerController._save_models": { "total": 0.10563086699949054, "count": 1, "self": 0.0035798230001091724, "children": { "RLTrainer._checkpoint": { "total": 0.10205104399938136, "count": 1, "self": 0.10205104399938136 } } } } } } }