{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5031392574310303, "min": 0.5031392574310303, "max": 1.4843417406082153, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15005.6259765625, "min": 15005.6259765625, "max": 45028.9921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.584220826625824, "min": -0.08828900754451752, "max": 0.584220826625824, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.087158203125, "min": -21.277650833129883, "max": 167.087158203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006124246399849653, "min": -0.02018110826611519, "max": 0.34502774477005005, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.7515344619750977, "min": -5.489261627197266, "max": 81.77157592773438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0646220137395652, "min": 0.06303003656685129, "max": 0.07534783958990358, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9047081923539129, "min": 0.5272183242393123, "max": 1.1125510491764028, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01583552552550654, "min": 0.00010024993043905144, "max": 0.016172320376513415, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2216973573570916, "min": 0.0013032490957076688, "max": 0.2299614259051547, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3855403953285725e-06, "min": 7.3855403953285725e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010339756553460001, "min": 0.00010339756553460001, "max": 0.0035072264309246007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246181428571431, "min": 0.10246181428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344654000000003, "min": 1.3691136000000002, "max": 2.5690754000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025593524714285717, "min": 0.00025593524714285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035830934600000006, "min": 0.0035830934600000006, "max": 0.11693063245999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007340338546782732, "min": 0.007340338546782732, "max": 0.3018491268157959, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10276474058628082, "min": 0.10276474058628082, "max": 2.1129438877105713, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.11538461538464, "min": 312.11538461538464, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32460.0, "min": 15984.0, "max": 32460.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.649629109403462, "min": -1.0000000521540642, "max": 1.6522674238265946, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.9117982685566, "min": -32.000001668930054, "max": 169.9117982685566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.649629109403462, "min": -1.0000000521540642, "max": 1.6522674238265946, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.9117982685566, "min": -32.000001668930054, "max": 169.9117982685566, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02347091564414, "min": 0.02347091564414, "max": 5.934065188281238, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.41750431134642, "min": 2.215900985946064, "max": 94.94504301249981, "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": "1678798415", "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": "1678800520" }, "total": 2104.783201426, "count": 1, "self": 0.48703701799922783, "children": { "run_training.setup": { "total": 0.10619650500007083, "count": 1, "self": 0.10619650500007083 }, "TrainerController.start_learning": { "total": 2104.1899679030003, "count": 1, "self": 1.3009188539977004, "children": { "TrainerController._reset_env": { "total": 9.496577512000044, "count": 1, "self": 9.496577512000044 }, "TrainerController.advance": { "total": 2093.2992521690026, "count": 63711, "self": 1.3820928570171418, "children": { "env_step": { "total": 1477.6975514859903, "count": 63711, "self": 1369.954555031012, "children": { "SubprocessEnvManager._take_step": { "total": 106.93049343199016, "count": 63711, "self": 4.66102086796775, "children": { "TorchPolicy.evaluate": { "total": 102.26947256402241, "count": 62564, "self": 102.26947256402241 } } }, "workers": { "total": 0.8125030229881531, "count": 63711, "self": 0.0, "children": { "worker_root": { "total": 2099.6648470889604, "count": 63711, "is_parallel": true, "self": 842.41011402294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007441072999995413, "count": 1, "is_parallel": true, "self": 0.005692861000056837, "children": { "_process_rank_one_or_two_observation": { "total": 0.001748211999938576, "count": 8, "is_parallel": true, "self": 0.001748211999938576 } } }, "UnityEnvironment.step": { "total": 0.043861004000063986, "count": 1, "is_parallel": true, "self": 0.0005143100000850609, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046648099998947146, "count": 1, "is_parallel": true, "self": 0.00046648099998947146 }, "communicator.exchange": { "total": 0.04131245400003536, "count": 1, "is_parallel": true, "self": 0.04131245400003536 }, "steps_from_proto": { "total": 0.0015677589999540942, "count": 1, "is_parallel": true, "self": 0.00036986600002819614, "children": { "_process_rank_one_or_two_observation": { "total": 0.001197892999925898, "count": 8, "is_parallel": true, "self": 0.001197892999925898 } } } } } } }, "UnityEnvironment.step": { "total": 1257.2547330660204, "count": 63710, "is_parallel": true, "self": 31.348623288039562, "children": { "UnityEnvironment._generate_step_input": { "total": 22.345214672016823, "count": 63710, "is_parallel": true, "self": 22.345214672016823 }, "communicator.exchange": { "total": 1113.5320890539642, "count": 63710, "is_parallel": true, "self": 1113.5320890539642 }, "steps_from_proto": { "total": 90.02880605199971, "count": 63710, "is_parallel": true, "self": 18.988197353034707, "children": { "_process_rank_one_or_two_observation": { "total": 71.040608698965, "count": 509680, "is_parallel": true, "self": 71.040608698965 } } } } } } } } } } }, "trainer_advance": { "total": 614.2196078259949, "count": 63711, "self": 2.441890037989083, "children": { "process_trajectory": { "total": 115.462639182001, "count": 63711, "self": 115.25970709000114, "children": { "RLTrainer._checkpoint": { "total": 0.2029320919998554, "count": 2, "self": 0.2029320919998554 } } }, "_update_policy": { "total": 496.3150786060048, "count": 438, "self": 312.65939298498324, "children": { "TorchPPOOptimizer.update": { "total": 183.65568562102158, "count": 22857, "self": 183.65568562102158 } } } } } } }, "trainer_threads": { "total": 1.0150001799047459e-06, "count": 1, "self": 1.0150001799047459e-06 }, "TrainerController._save_models": { "total": 0.09321835299988379, "count": 1, "self": 0.001462826000079076, "children": { "RLTrainer._checkpoint": { "total": 0.09175552699980472, "count": 1, "self": 0.09175552699980472 } } } } } } }