{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5671671032905579, "min": 0.5671671032905579, "max": 1.4436455965042114, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17033.162109375, "min": 17033.162109375, "max": 43794.43359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5754985213279724, "min": -0.10258052498102188, "max": 0.5824079513549805, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.29058837890625, "min": -24.927066802978516, "max": 165.4038543701172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.06394016742706299, "min": -0.06394016742706299, "max": 0.35053372383117676, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -18.0311279296875, "min": -18.0311279296875, "max": 83.07649230957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0702031629250592, "min": 0.06619880732753138, "max": 0.07339590215165767, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.053047443875888, "min": 0.5137713150616037, "max": 1.053047443875888, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01794834718683786, "min": 0.0002900829543136433, "max": 0.019909722254461876, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2692252078025679, "min": 0.004061161360391006, "max": 0.27873611156246625, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.419597526833336e-06, "min": 7.419597526833336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011129396290250004, "min": 0.00011129396290250004, "max": 0.0036331330889556998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247316666666668, "min": 0.10247316666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5370975000000002, "min": 1.3886848, "max": 2.6110442999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025706935, "min": 0.00025706935, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038560402500000006, "min": 0.0038560402500000006, "max": 0.12112332557000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010825072415173054, "min": 0.01015456486493349, "max": 0.3324744999408722, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16237609088420868, "min": 0.14216390252113342, "max": 2.3273215293884277, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.4719101123595, "min": 309.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28611.0, "min": 15984.0, "max": 32668.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6560449313079373, "min": -1.0000000521540642, "max": 1.6616417439756812, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.38799888640642, "min": -30.995201610028744, "max": 165.04899854958057, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6560449313079373, "min": -1.0000000521540642, "max": 1.6616417439756812, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.38799888640642, "min": -30.995201610028744, "max": 165.04899854958057, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03634270197432946, "min": 0.032868223816767565, "max": 6.83444485347718, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.234500475715322, "min": 3.131070501056456, "max": 109.35111765563488, "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": "1703517003", "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": "1703519231" }, "total": 2228.0305342889997, "count": 1, "self": 0.6534944110007928, "children": { "run_training.setup": { "total": 0.0563965699993787, "count": 1, "self": 0.0563965699993787 }, "TrainerController.start_learning": { "total": 2227.3206433079995, "count": 1, "self": 2.1007193750056103, "children": { "TrainerController._reset_env": { "total": 2.205991990000257, "count": 1, "self": 2.205991990000257 }, "TrainerController.advance": { "total": 2222.956130341994, "count": 63861, "self": 2.0510763020829472, "children": { "env_step": { "total": 1509.6926524459295, "count": 63861, "self": 1382.3562625148434, "children": { "SubprocessEnvManager._take_step": { "total": 126.10974500001703, "count": 63861, "self": 4.8086407979417345, "children": { "TorchPolicy.evaluate": { "total": 121.3011042020753, "count": 62554, "self": 121.3011042020753 } } }, "workers": { "total": 1.2266449310691314, "count": 63861, "self": 0.0, "children": { "worker_root": { "total": 2223.068679779074, "count": 63861, "is_parallel": true, "self": 970.4035015570416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013806999995722435, "count": 1, "is_parallel": true, "self": 0.00041244999829359585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009682500012786477, "count": 8, "is_parallel": true, "self": 0.0009682500012786477 } } }, "UnityEnvironment.step": { "total": 0.04531978999966668, "count": 1, "is_parallel": true, "self": 0.0005633099990518531, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026123000043298816, "count": 1, "is_parallel": true, "self": 0.00026123000043298816 }, "communicator.exchange": { "total": 0.04308442000001378, "count": 1, "is_parallel": true, "self": 0.04308442000001378 }, "steps_from_proto": { "total": 0.0014108300001680618, "count": 1, "is_parallel": true, "self": 0.0002990000002682791, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011118299998997827, "count": 8, "is_parallel": true, "self": 0.0011118299998997827 } } } } } } }, "UnityEnvironment.step": { "total": 1252.6651782220324, "count": 63860, "is_parallel": true, "self": 34.92733187217982, "children": { "UnityEnvironment._generate_step_input": { "total": 19.586493822932425, "count": 63860, "is_parallel": true, "self": 19.586493822932425 }, "communicator.exchange": { "total": 1101.2546276129988, "count": 63860, "is_parallel": true, "self": 1101.2546276129988 }, "steps_from_proto": { "total": 96.89672491392139, "count": 63860, "is_parallel": true, "self": 20.76002368598529, "children": { "_process_rank_one_or_two_observation": { "total": 76.1367012279361, "count": 510880, "is_parallel": true, "self": 76.1367012279361 } } } } } } } } } } }, "trainer_advance": { "total": 711.2124015939817, "count": 63861, "self": 3.68536197679623, "children": { "process_trajectory": { "total": 117.70001922418123, "count": 63861, "self": 117.57851627418222, "children": { "RLTrainer._checkpoint": { "total": 0.12150294999901234, "count": 2, "self": 0.12150294999901234 } } }, "_update_policy": { "total": 589.8270203930042, "count": 453, "self": 240.60977506203744, "children": { "TorchPPOOptimizer.update": { "total": 349.21724533096676, "count": 22809, "self": 349.21724533096676 } } } } } } }, "trainer_threads": { "total": 9.599998520570807e-07, "count": 1, "self": 9.599998520570807e-07 }, "TrainerController._save_models": { "total": 0.05780064099963056, "count": 1, "self": 0.001257710999198025, "children": { "RLTrainer._checkpoint": { "total": 0.056542930000432534, "count": 1, "self": 0.056542930000432534 } } } } } } }