| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.34739741683006287, |
| "min": 0.3409183621406555, |
| "max": 1.471137285232544, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10533.08984375, |
| "min": 10227.55078125, |
| "max": 44628.421875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989917.0, |
| "min": 29952.0, |
| "max": 989917.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989917.0, |
| "min": 29952.0, |
| "max": 989917.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5200357437133789, |
| "min": -0.10653695464134216, |
| "max": 0.5748505592346191, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 143.5298614501953, |
| "min": -25.56886863708496, |
| "max": 160.38330078125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.004392037633806467, |
| "min": -0.048593152314424515, |
| "max": 0.1942993849515915, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.2122024297714233, |
| "min": -12.828592300415039, |
| "max": 46.63185119628906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06770979517919837, |
| "min": 0.06366556847215497, |
| "max": 0.0748222426013667, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9479371325087771, |
| "min": 0.48662292316218786, |
| "max": 1.0257809395621094, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01524388548727793, |
| "min": 0.0009409967874436435, |
| "max": 0.016492384168992028, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21341439682189103, |
| "min": 0.009005430256219442, |
| "max": 0.24738576253488043, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.296890424878575e-06, |
| "min": 7.296890424878575e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010215646594830005, |
| "min": 0.00010215646594830005, |
| "max": 0.0035079236306922003, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10243226428571431, |
| "min": 0.10243226428571431, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4340517000000004, |
| "min": 1.3691136000000002, |
| "max": 2.5693078, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002529832021428573, |
| "min": 0.0002529832021428573, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003541764830000002, |
| "min": 0.003541764830000002, |
| "max": 0.11695384921999999, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012490363791584969, |
| "min": 0.012426632456481457, |
| "max": 0.39465638995170593, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17486509680747986, |
| "min": 0.17486509680747986, |
| "max": 2.762594699859619, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 362.45454545454544, |
| "min": 345.4047619047619, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31896.0, |
| "min": 15984.0, |
| "max": 33059.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.523870431225408, |
| "min": -1.0000000521540642, |
| "max": 1.6289811639224783, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 134.10059794783592, |
| "min": -32.000001668930054, |
| "max": 138.46339893341064, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.523870431225408, |
| "min": -1.0000000521540642, |
| "max": 1.6289811639224783, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 134.10059794783592, |
| "min": -32.000001668930054, |
| "max": 138.46339893341064, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04649343963484915, |
| "min": 0.0447871651815062, |
| "max": 7.6034834096208215, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.091422687866725, |
| "min": 3.762121875246521, |
| "max": 121.65573455393314, |
| "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": "1773171104", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "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": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1773173438" |
| }, |
| "total": 2334.102716694, |
| "count": 1, |
| "self": 0.4777660189997732, |
| "children": { |
| "run_training.setup": { |
| "total": 0.025251552000099764, |
| "count": 1, |
| "self": 0.025251552000099764 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2333.599699123, |
| "count": 1, |
| "self": 1.4084689630276443, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.2222639450001225, |
| "count": 1, |
| "self": 2.2222639450001225 |
| }, |
| "TrainerController.advance": { |
| "total": 2329.892558908973, |
| "count": 63767, |
| "self": 1.4076772949101723, |
| "children": { |
| "env_step": { |
| "total": 1652.7477334830487, |
| "count": 63767, |
| "self": 1494.9276467291088, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 156.9722953919022, |
| "count": 63767, |
| "self": 4.738109924827313, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 152.2341854670749, |
| "count": 62565, |
| "self": 152.2341854670749 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8477913620376967, |
| "count": 63767, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2326.7400841720428, |
| "count": 63767, |
| "is_parallel": true, |
| "self": 953.6305176191395, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002001575000122102, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006589019999410084, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013426730001810938, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013426730001810938 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.09599848800007749, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006222779998097394, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004404200003591541, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004404200003591541 |
| }, |
| "communicator.exchange": { |
| "total": 0.09321775699982027, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.09321775699982027 |
| }, |
| "steps_from_proto": { |
| "total": 0.001718033000088326, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00037135300090085366, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013466799991874723, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013466799991874723 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1373.1095665529033, |
| "count": 63766, |
| "is_parallel": true, |
| "self": 34.63509333480533, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.957856755069315, |
| "count": 63766, |
| "is_parallel": true, |
| "self": 23.957856755069315 |
| }, |
| "communicator.exchange": { |
| "total": 1201.3745727711366, |
| "count": 63766, |
| "is_parallel": true, |
| "self": 1201.3745727711366 |
| }, |
| "steps_from_proto": { |
| "total": 113.14204369189201, |
| "count": 63766, |
| "is_parallel": true, |
| "self": 23.795270022806562, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 89.34677366908545, |
| "count": 510128, |
| "is_parallel": true, |
| "self": 89.34677366908545 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 675.7371481310142, |
| "count": 63767, |
| "self": 2.656185389098482, |
| "children": { |
| "process_trajectory": { |
| "total": 127.95774398691447, |
| "count": 63767, |
| "self": 127.7600758829144, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19766810400005852, |
| "count": 2, |
| "self": 0.19766810400005852 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 545.1232187550013, |
| "count": 447, |
| "self": 301.23969948292824, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 243.88351927207304, |
| "count": 22767, |
| "self": 243.88351927207304 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.859995770966634e-07, |
| "count": 1, |
| "self": 9.859995770966634e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.076406319999478, |
| "count": 1, |
| "self": 0.001042525998855126, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07536379400062287, |
| "count": 1, |
| "self": 0.07536379400062287 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
