{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6735891699790955, "min": 0.6626113057136536, "max": 1.5026880502700806, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20132.232421875, "min": 20058.5703125, "max": 45585.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39983412623405457, "min": -0.10854578018188477, "max": 0.42115992307662964, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.35588073730469, "min": -26.15953254699707, "max": 111.18621826171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00027918186970055103, "min": 0.00027918186970055103, "max": 0.44015491008758545, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.07426238059997559, "min": 0.07426238059997559, "max": 104.31671142578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669718371299539, "min": 0.06297868117551497, "max": 0.077070477683714, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9376057198193547, "min": 0.5111571991108305, "max": 1.027595369533325, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014820844551217136, "min": 0.0007329715438957437, "max": 0.014820844551217136, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2074918237170399, "min": 0.006791231853242806, "max": 0.2074918237170399, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.687276009035715e-06, "min": 7.687276009035715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001076218641265, "min": 0.0001076218641265, "max": 0.003506367231210999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256239285714286, "min": 0.10256239285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358735, "min": 1.3691136000000002, "max": 2.5687889999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026598304642857145, "min": 0.00026598304642857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037237626500000007, "min": 0.0037237626500000007, "max": 0.11690202109999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006753682624548674, "min": 0.006753682624548674, "max": 0.28607282042503357, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09455155581235886, "min": 0.09455155581235886, "max": 2.002509832382202, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 444.9710144927536, "min": 444.9710144927536, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30703.0, "min": 15984.0, "max": 32768.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.439057947176954, "min": -1.0000000521540642, "max": 1.4542984332029636, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.29499835520983, "min": -32.000001668930054, "max": 99.29499835520983, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.439057947176954, "min": -1.0000000521540642, "max": 1.4542984332029636, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.29499835520983, "min": -32.000001668930054, "max": 99.29499835520983, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0316500205845459, "min": 0.0316500205845459, "max": 5.376601179130375, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.183851420333667, "min": 2.117676504421979, "max": 86.025618866086, "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": "1680445503", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/mnt/slurm-home/h_kambe/miniconda3/envs/py39-deep-rl-class/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": "1.8.2+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1680446378" }, "total": 875.3217076994479, "count": 1, "self": 1.2227294314652681, "children": { "run_training.setup": { "total": 0.06688017770648003, "count": 1, "self": 0.06688017770648003 }, "TrainerController.start_learning": { "total": 874.0320980902761, "count": 1, "self": 0.841011643409729, "children": { "TrainerController._reset_env": { "total": 4.5903076576069, "count": 1, "self": 4.5903076576069 }, "TrainerController.advance": { "total": 868.4596434375271, "count": 63470, "self": 0.8723670179024339, "children": { "env_step": { "total": 510.86544440779835, "count": 63470, "self": 442.84755695890635, "children": { "SubprocessEnvManager._take_step": { "total": 67.4842429868877, "count": 63470, "self": 2.6989240841940045, "children": { "TorchPolicy.evaluate": { "total": 64.78531890269369, "count": 62567, "self": 64.78531890269369 } } }, "workers": { "total": 0.5336444620043039, "count": 63470, "self": 0.0, "children": { "worker_root": { "total": 872.7189337704331, "count": 63470, "is_parallel": true, "self": 486.3338545449078, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009547211229801178, "count": 1, "is_parallel": true, "self": 0.0002779560163617134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006767651066184044, "count": 8, "is_parallel": true, "self": 0.0006767651066184044 } } }, "UnityEnvironment.step": { "total": 0.01919824816286564, "count": 1, "is_parallel": true, "self": 0.00019722618162631989, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017944443970918655, "count": 1, "is_parallel": true, "self": 0.00017944443970918655 }, "communicator.exchange": { "total": 0.018152287229895592, "count": 1, "is_parallel": true, "self": 0.018152287229895592 }, "steps_from_proto": { "total": 0.0006692903116345406, "count": 1, "is_parallel": true, "self": 0.0001616617664694786, "children": { "_process_rank_one_or_two_observation": { "total": 0.000507628545165062, "count": 8, "is_parallel": true, "self": 0.000507628545165062 } } } } } } }, "UnityEnvironment.step": { "total": 386.38507922552526, "count": 63469, "is_parallel": true, "self": 11.984847588464618, "children": { "UnityEnvironment._generate_step_input": { "total": 8.824708512052894, "count": 63469, "is_parallel": true, "self": 8.824708512052894 }, "communicator.exchange": { "total": 328.28179231472313, "count": 63469, "is_parallel": true, "self": 328.28179231472313 }, "steps_from_proto": { "total": 37.293730810284615, "count": 63469, "is_parallel": true, "self": 9.112111668102443, "children": { "_process_rank_one_or_two_observation": { "total": 28.18161914218217, "count": 507752, "is_parallel": true, "self": 28.18161914218217 } } } } } } } } } } }, "trainer_advance": { "total": 356.72183201182634, "count": 63470, "self": 1.3909351788461208, "children": { "process_trajectory": { "total": 62.483430250547826, "count": 63470, "self": 62.21348575130105, "children": { "RLTrainer._checkpoint": { "total": 0.2699444992467761, "count": 2, "self": 0.2699444992467761 } } }, "_update_policy": { "total": 292.8474665824324, "count": 444, "self": 182.30571756884456, "children": { "TorchPPOOptimizer.update": { "total": 110.54174901358783, "count": 22806, "self": 110.54174901358783 } } } } } } }, "trainer_threads": { "total": 6.379559636116028e-07, "count": 1, "self": 6.379559636116028e-07 }, "TrainerController._save_models": { "total": 0.14113471377640963, "count": 1, "self": 0.008731045760214329, "children": { "RLTrainer._checkpoint": { "total": 0.1324036680161953, "count": 1, "self": 0.1324036680161953 } } } } } } }