{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3767079710960388, "min": 0.3603907525539398, "max": 1.3775832653045654, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11482.05859375, "min": 10938.6328125, "max": 41790.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29950.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29950.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6537896394729614, "min": -0.09571461379528046, "max": 0.7146927714347839, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.25277709960938, "min": -23.16293716430664, "max": 202.97274780273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013126983307301998, "min": -0.013126983307301998, "max": 0.3322901427745819, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.8199522495269775, "min": -3.8199522495269775, "max": 80.41421508789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850352072520072, "min": 0.06501737563978947, "max": 0.07266703175388732, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.95904929015281, "min": 0.4887095246935363, "max": 1.0690438598263141, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015304034145845523, "min": 0.0012501317510022977, "max": 0.017409728616940196, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2142564780418373, "min": 0.015001581012027573, "max": 0.26114592925410296, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.652154592171427e-06, "min": 7.652154592171427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010713016429039998, "min": 0.00010713016429039998, "max": 0.0035108144297286, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255068571428573, "min": 0.10255068571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357096000000003, "min": 1.3886848, "max": 2.5726288999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026481350285714283, "min": 0.00026481350285714283, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00370738904, "min": 0.00370738904, "max": 0.11705011286000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012179279699921608, "min": 0.012179279699921608, "max": 0.48961400985717773, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1705099195241928, "min": 0.1705099195241928, "max": 3.427298069000244, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 287.8611111111111, "min": 263.58490566037733, "max": 992.7647058823529, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31089.0, "min": 16877.0, "max": 32559.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6380444260797016, "min": -0.9166774696880772, "max": 1.7175377281909843, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.90879801660776, "min": -28.41700156033039, "max": 182.05899918824434, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6380444260797016, "min": -0.9166774696880772, "max": 1.7175377281909843, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.90879801660776, "min": -28.41700156033039, "max": 182.05899918824434, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036504639946845906, "min": 0.03488895420055344, "max": 9.440492033958435, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9425011142593576, "min": 3.698229145258665, "max": 160.4883645772934, "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": "1680185173", "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=PyramidsTraining --no-graphics --force", "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": "1680188902" }, "total": 3729.2332885799997, "count": 1, "self": 0.6360896849996607, "children": { "run_training.setup": { "total": 0.22420987099985723, "count": 1, "self": 0.22420987099985723 }, "TrainerController.start_learning": { "total": 3728.372989024, "count": 1, "self": 2.7185400809812563, "children": { "TrainerController._reset_env": { "total": 8.097107924000056, "count": 1, "self": 8.097107924000056 }, "TrainerController.advance": { "total": 3717.44264125302, "count": 64332, "self": 2.740464870950291, "children": { "env_step": { "total": 2507.0804178620783, "count": 64332, "self": 2350.538354326012, "children": { "SubprocessEnvManager._take_step": { "total": 154.88101418704355, "count": 64332, "self": 7.631342795039245, "children": { "TorchPolicy.evaluate": { "total": 147.2496713920043, "count": 62563, "self": 147.2496713920043 } } }, "workers": { "total": 1.66104934902296, "count": 64332, "self": 0.0, "children": { "worker_root": { "total": 3720.5877042390007, "count": 64332, "is_parallel": true, "self": 1569.5671120189477, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005300024000007397, "count": 1, "is_parallel": true, "self": 0.0018187630000738864, "children": { "_process_rank_one_or_two_observation": { "total": 0.003481260999933511, "count": 8, "is_parallel": true, "self": 0.003481260999933511 } } }, "UnityEnvironment.step": { "total": 0.06608677999997781, "count": 1, "is_parallel": true, "self": 0.0006233780002276035, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005760399999417132, "count": 1, "is_parallel": true, "self": 0.0005760399999417132 }, "communicator.exchange": { "total": 0.06274657399990247, "count": 1, "is_parallel": true, "self": 0.06274657399990247 }, "steps_from_proto": { "total": 0.002140787999906024, "count": 1, "is_parallel": true, "self": 0.00047031500002958637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016704729998764378, "count": 8, "is_parallel": true, "self": 0.0016704729998764378 } } } } } } }, "UnityEnvironment.step": { "total": 2151.020592220053, "count": 64331, "is_parallel": true, "self": 45.72248392217534, "children": { "UnityEnvironment._generate_step_input": { "total": 27.825075067922626, "count": 64331, "is_parallel": true, "self": 27.825075067922626 }, "communicator.exchange": { "total": 1942.5127014570287, "count": 64331, "is_parallel": true, "self": 1942.5127014570287 }, "steps_from_proto": { "total": 134.96033177292634, "count": 64331, "is_parallel": true, "self": 30.995202369732397, "children": { "_process_rank_one_or_two_observation": { "total": 103.96512940319394, "count": 514648, "is_parallel": true, "self": 103.96512940319394 } } } } } } } } } } }, "trainer_advance": { "total": 1207.6217585199915, "count": 64332, "self": 5.360714091009868, "children": { "process_trajectory": { "total": 177.20507640198684, "count": 64332, "self": 176.9228533069877, "children": { "RLTrainer._checkpoint": { "total": 0.28222309499915355, "count": 2, "self": 0.28222309499915355 } } }, "_update_policy": { "total": 1025.0559680269948, "count": 456, "self": 420.78344789397875, "children": { "TorchPPOOptimizer.update": { "total": 604.2725201330161, "count": 22791, "self": 604.2725201330161 } } } } } } }, "trainer_threads": { "total": 1.050999344442971e-06, "count": 1, "self": 1.050999344442971e-06 }, "TrainerController._save_models": { "total": 0.11469871499957662, "count": 1, "self": 0.0035911059994759853, "children": { "RLTrainer._checkpoint": { "total": 0.11110760900010064, "count": 1, "self": 0.11110760900010064 } } } } } } }