{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5035953521728516, "min": 0.5035953521728516, "max": 1.4379850625991821, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15043.400390625, "min": 15043.400390625, "max": 43622.71484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2050670087337494, "min": -0.10670418292284012, "max": 0.2859508693218231, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.08702087402344, "min": -25.502300262451172, "max": 72.91747283935547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011508926749229431, "min": 0.0014740669867023826, "max": 0.5478800535202026, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.923267364501953, "min": 0.37883520126342773, "max": 131.4912109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07093967307688824, "min": 0.06461270906080697, "max": 0.07646107029064471, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9931554230764353, "min": 0.5352274920345129, "max": 1.0399806459078236, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009738692429621625, "min": 0.00010014682939214777, "max": 0.03460518842125126, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13634169401470275, "min": 0.001301908782097921, "max": 0.2422363189487588, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.72784028122857e-06, "min": 7.72784028122857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001081897639372, "min": 0.0001081897639372, "max": 0.0035072720309093993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257591428571429, "min": 0.10257591428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360628, "min": 1.3886848, "max": 2.5690906, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002673338371428571, "min": 0.0002673338371428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037426737199999995, "min": 0.0037426737199999995, "max": 0.11693215094000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.020072313025593758, "min": 0.019238946959376335, "max": 0.806215763092041, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2810123860836029, "min": 0.2693452537059784, "max": 5.643510341644287, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 642.3877551020408, "min": 565.0196078431372, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31477.0, "min": 15984.0, "max": 34446.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8268366980613494, "min": -1.0000000521540642, "max": 1.199619578234121, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.51499820500612, "min": -31.994401678442955, "max": 61.18059848994017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8268366980613494, "min": -1.0000000521540642, "max": 1.199619578234121, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.51499820500612, "min": -31.994401678442955, "max": 61.18059848994017, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13252249017906642, "min": 0.11538690647313499, "max": 18.014705112203956, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.493602018774254, "min": 5.77399624150712, "max": 288.2352817952633, "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": "1704303421", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704305478" }, "total": 2056.268125153, "count": 1, "self": 0.441295154999807, "children": { "run_training.setup": { "total": 0.067127414999959, "count": 1, "self": 0.067127414999959 }, "TrainerController.start_learning": { "total": 2055.759702583, "count": 1, "self": 1.3303042309485136, "children": { "TrainerController._reset_env": { "total": 2.5446582939998734, "count": 1, "self": 2.5446582939998734 }, "TrainerController.advance": { "total": 2051.8035852660514, "count": 63243, "self": 1.3608836220355442, "children": { "env_step": { "total": 1425.5616158519956, "count": 63243, "self": 1297.1571386719836, "children": { "SubprocessEnvManager._take_step": { "total": 127.58667744800073, "count": 63243, "self": 4.602934214007519, "children": { "TorchPolicy.evaluate": { "total": 122.98374323399321, "count": 62563, "self": 122.98374323399321 } } }, "workers": { "total": 0.8177997320112809, "count": 63243, "self": 0.0, "children": { "worker_root": { "total": 2050.8907973959926, "count": 63243, "is_parallel": true, "self": 869.4558306010458, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003595559000132198, "count": 1, "is_parallel": true, "self": 0.0005844669999532925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030110920001789054, "count": 8, "is_parallel": true, "self": 0.0030110920001789054 } } }, "UnityEnvironment.step": { "total": 0.049581873999841264, "count": 1, "is_parallel": true, "self": 0.000590293000186648, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004887779998625774, "count": 1, "is_parallel": true, "self": 0.0004887779998625774 }, "communicator.exchange": { "total": 0.046865762999914296, "count": 1, "is_parallel": true, "self": 0.046865762999914296 }, "steps_from_proto": { "total": 0.001637039999877743, "count": 1, "is_parallel": true, "self": 0.0003652320001492626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012718079997284804, "count": 8, "is_parallel": true, "self": 0.0012718079997284804 } } } } } } }, "UnityEnvironment.step": { "total": 1181.4349667949468, "count": 63242, "is_parallel": true, "self": 34.94937868697457, "children": { "UnityEnvironment._generate_step_input": { "total": 24.654840195989436, "count": 63242, "is_parallel": true, "self": 24.654840195989436 }, "communicator.exchange": { "total": 1024.7032089319518, "count": 63242, "is_parallel": true, "self": 1024.7032089319518 }, "steps_from_proto": { "total": 97.12753898003098, "count": 63242, "is_parallel": true, "self": 19.21192991298153, "children": { "_process_rank_one_or_two_observation": { "total": 77.91560906704945, "count": 505936, "is_parallel": true, "self": 77.91560906704945 } } } } } } } } } } }, "trainer_advance": { "total": 624.8810857920203, "count": 63243, "self": 2.5783959119689825, "children": { "process_trajectory": { "total": 122.02269618205196, "count": 63243, "self": 121.83477317605161, "children": { "RLTrainer._checkpoint": { "total": 0.1879230060003465, "count": 2, "self": 0.1879230060003465 } } }, "_update_policy": { "total": 500.2799936979993, "count": 444, "self": 296.8824081130183, "children": { "TorchPPOOptimizer.update": { "total": 203.39758558498102, "count": 22758, "self": 203.39758558498102 } } } } } } }, "trainer_threads": { "total": 8.930001058615744e-07, "count": 1, "self": 8.930001058615744e-07 }, "TrainerController._save_models": { "total": 0.08115389900012815, "count": 1, "self": 0.001341434000096342, "children": { "RLTrainer._checkpoint": { "total": 0.07981246500003181, "count": 1, "self": 0.07981246500003181 } } } } } } }