| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3769102692604065, |
| "min": 0.3769102692604065, |
| "max": 1.4772335290908813, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11253.033203125, |
| "min": 11253.033203125, |
| "max": 44813.35546875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989922.0, |
| "min": 29997.0, |
| "max": 989922.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989922.0, |
| "min": 29997.0, |
| "max": 989922.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4839579164981842, |
| "min": -0.22699061036109924, |
| "max": 0.4853375256061554, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 133.0884246826172, |
| "min": -54.023765563964844, |
| "max": 134.923828125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0004888285766355693, |
| "min": -0.0021691294386982918, |
| "max": 0.22537043690681458, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 0.13442786037921906, |
| "min": -0.5618045330047607, |
| "max": 54.314273834228516, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0669404070566608, |
| "min": 0.06512009097909637, |
| "max": 0.07308214517099364, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9371656987932511, |
| "min": 0.563944766701993, |
| "max": 1.0501324327348154, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01595665088617742, |
| "min": 0.00038315077133163584, |
| "max": 0.01678158699637933, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.22339311240648385, |
| "min": 0.004214658484647994, |
| "max": 0.25172380494568997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.325883272357142e-06, |
| "min": 7.325883272357142e-06, |
| "max": 0.0002948493392168875, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.000102562365813, |
| "min": 0.000102562365813, |
| "max": 0.0031370183543273, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244192857142857, |
| "min": 0.10244192857142857, |
| "max": 0.1982831125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.434187, |
| "min": 1.434187, |
| "max": 2.4428280000000004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002539486642857142, |
| "min": 0.0002539486642857142, |
| "max": 0.00982848293875, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035552812999999988, |
| "min": 0.0035552812999999988, |
| "max": 0.10459270273000003, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007794955279678106, |
| "min": 0.007794955279678106, |
| "max": 0.34045690298080444, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10912937670946121, |
| "min": 0.10912937670946121, |
| "max": 2.7236552238464355, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 388.0375, |
| "min": 388.0375, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31043.0, |
| "min": 16412.0, |
| "max": 32140.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5369474770501257, |
| "min": -1.0000000521540642, |
| "max": 1.5384609543877403, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 122.95579816401005, |
| "min": -32.000001668930054, |
| "max": 126.15379825979471, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5369474770501257, |
| "min": -1.0000000521540642, |
| "max": 1.5384609543877403, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 122.95579816401005, |
| "min": -32.000001668930054, |
| "max": 126.15379825979471, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.03153176446667203, |
| "min": 0.03153176446667203, |
| "max": 6.869198814911001, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.5225411573337624, |
| "min": 2.380161932189367, |
| "max": 116.77637985348701, |
| "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": "1742785152", |
| "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": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1742787780" |
| }, |
| "total": 2627.616837402, |
| "count": 1, |
| "self": 0.8911775390001822, |
| "children": { |
| "run_training.setup": { |
| "total": 0.028885014000024967, |
| "count": 1, |
| "self": 0.028885014000024967 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2626.6967748489997, |
| "count": 1, |
| "self": 1.865954757048712, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.465599083000143, |
| "count": 1, |
| "self": 2.465599083000143 |
| }, |
| "TrainerController.advance": { |
| "total": 2622.258755343951, |
| "count": 63616, |
| "self": 1.787203052987934, |
| "children": { |
| "env_step": { |
| "total": 1676.2333711220222, |
| "count": 63616, |
| "self": 1542.325259395147, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 132.86306784900444, |
| "count": 63616, |
| "self": 5.449936877111213, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 127.41313097189322, |
| "count": 62560, |
| "self": 127.41313097189322 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.0450438778707394, |
| "count": 63616, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2621.0285192820224, |
| "count": 63616, |
| "is_parallel": true, |
| "self": 1214.5738495990595, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0038643049997517664, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0013387129993134295, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002525592000438337, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002525592000438337 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05262987100013561, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005615790000774723, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00044968500014874735, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00044968500014874735 |
| }, |
| "communicator.exchange": { |
| "total": 0.049898462999863114, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.049898462999863114 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017201440000462753, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036873700037176604, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013514069996745093, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013514069996745093 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1406.454669682963, |
| "count": 63615, |
| "is_parallel": true, |
| "self": 36.4811207101061, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 26.284732955845357, |
| "count": 63615, |
| "is_parallel": true, |
| "self": 26.284732955845357 |
| }, |
| "communicator.exchange": { |
| "total": 1236.4054507000028, |
| "count": 63615, |
| "is_parallel": true, |
| "self": 1236.4054507000028 |
| }, |
| "steps_from_proto": { |
| "total": 107.2833653170087, |
| "count": 63615, |
| "is_parallel": true, |
| "self": 22.31307090372593, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 84.97029441328277, |
| "count": 508920, |
| "is_parallel": true, |
| "self": 84.97029441328277 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 944.2381811689411, |
| "count": 63616, |
| "self": 3.4219198839036835, |
| "children": { |
| "process_trajectory": { |
| "total": 138.42693040203994, |
| "count": 63616, |
| "self": 138.21578509103892, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.21114531100101885, |
| "count": 2, |
| "self": 0.21114531100101885 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 802.3893308829975, |
| "count": 445, |
| "self": 321.1659384499426, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 481.22339243305487, |
| "count": 22845, |
| "self": 481.22339243305487 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.2749997040373273e-06, |
| "count": 1, |
| "self": 1.2749997040373273e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10646438999992824, |
| "count": 1, |
| "self": 0.002633774999594607, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10383061500033364, |
| "count": 1, |
| "self": 0.10383061500033364 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
