| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.00976257212460041, |
| "min": 0.00810762494802475, |
| "max": 1.333135962486267, |
| "count": 56 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 292.4085693359375, |
| "min": 242.83956909179688, |
| "max": 40442.01171875, |
| "count": 56 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1679922.0, |
| "min": 29952.0, |
| "max": 1679922.0, |
| "count": 56 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1679922.0, |
| "min": 29952.0, |
| "max": 1679922.0, |
| "count": 56 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.1003979966044426, |
| "min": -0.11700891703367233, |
| "max": -0.05024002119898796, |
| "count": 56 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -24.09552001953125, |
| "min": -28.08213996887207, |
| "max": -11.906885147094727, |
| "count": 56 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 1.658780813217163, |
| "min": 0.8971594572067261, |
| "max": 1.7411118745803833, |
| "count": 56 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 398.1073913574219, |
| "min": 212.6267852783203, |
| "max": 419.60797119140625, |
| "count": 56 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06546054518608471, |
| "min": 0.0632256495570653, |
| "max": 0.07468554110925955, |
| "count": 56 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.8509870874191013, |
| "min": 0.4881465304907192, |
| "max": 0.9709120344203742, |
| "count": 56 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0016016615746402515, |
| "min": 0.0010882390541183458, |
| "max": 0.02384121062582956, |
| "count": 56 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.02082160047032327, |
| "min": 0.014147107703538496, |
| "max": 0.16688847438080692, |
| "count": 56 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00013350662472857947, |
| "min": 0.00013350662472857947, |
| "max": 0.00029838354339596195, |
| "count": 56 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0017355861214715333, |
| "min": 0.0017355861214715333, |
| "max": 0.0031012485662505664, |
| "count": 56 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.14450218974358975, |
| "min": 0.14450218974358975, |
| "max": 0.19946118095238097, |
| "count": 56 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.8785284666666668, |
| "min": 1.3897045333333333, |
| "max": 2.400965666666666, |
| "count": 56 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.004455768755384615, |
| "min": 0.004455768755384615, |
| "max": 0.009946171977142856, |
| "count": 56 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.05792499381999999, |
| "min": 0.05792499381999999, |
| "max": 0.10340156839, |
| "count": 56 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 1.6494263410568237, |
| "min": 0.8748728632926941, |
| "max": 1.6680957078933716, |
| "count": 56 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 21.442543029785156, |
| "min": 6.124110221862793, |
| "max": 23.297218322753906, |
| "count": 56 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 999.0, |
| "min": 945.8181818181819, |
| "max": 999.0, |
| "count": 56 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31968.0, |
| "min": 15984.0, |
| "max": 32672.0, |
| "count": 56 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.9998129548565033, |
| "min": -1.0000000521540642, |
| "max": -0.825375806201588, |
| "count": 56 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -30.994201600551605, |
| "min": -32.000001668930054, |
| "max": -15.99960083514452, |
| "count": 56 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.9998129548565033, |
| "min": -1.0000000521540642, |
| "max": -0.825375806201588, |
| "count": 56 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -30.994201600551605, |
| "min": -32.000001668930054, |
| "max": -15.99960083514452, |
| "count": 56 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 16.324769891077473, |
| "min": 8.921613211743534, |
| "max": 16.791567413023703, |
| "count": 56 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 506.06786662340164, |
| "min": 255.10047686100006, |
| "max": 532.9510239064693, |
| "count": 56 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 56 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 56 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1739545124", |
| "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": "1739548199" |
| }, |
| "total": 3074.677906106, |
| "count": 1, |
| "self": 0.34473998900011793, |
| "children": { |
| "run_training.setup": { |
| "total": 0.02003658900002847, |
| "count": 1, |
| "self": 0.02003658900002847 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3074.313129528, |
| "count": 1, |
| "self": 2.128562497913663, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.8911349290001453, |
| "count": 1, |
| "self": 2.8911349290001453 |
| }, |
| "TrainerController.advance": { |
| "total": 3069.161393537086, |
| "count": 105929, |
| "self": 2.481262319097368, |
| "children": { |
| "env_step": { |
| "total": 1935.6369290010005, |
| "count": 105929, |
| "self": 1678.1288984050368, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 256.2271858299928, |
| "count": 105929, |
| "self": 7.6624295839949355, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 248.56475624599784, |
| "count": 105529, |
| "self": 248.56475624599784 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.280844765970869, |
| "count": 105929, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3066.6013888071584, |
| "count": 105929, |
| "is_parallel": true, |
| "self": 1568.3899024171662, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0024217509999289177, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00071093200017458, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0017108189997543377, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0017108189997543377 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.050344865999932153, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005354560000796482, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000481322999803524, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000481322999803524 |
| }, |
| "communicator.exchange": { |
| "total": 0.04773205500009681, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04773205500009681 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015960319999521744, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003362119998655544, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00125982000008662, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00125982000008662 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1498.2114863899922, |
| "count": 105928, |
| "is_parallel": true, |
| "self": 52.76834128602991, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 38.9807330930189, |
| "count": 105928, |
| "is_parallel": true, |
| "self": 38.9807330930189 |
| }, |
| "communicator.exchange": { |
| "total": 1247.517861665954, |
| "count": 105928, |
| "is_parallel": true, |
| "self": 1247.517861665954 |
| }, |
| "steps_from_proto": { |
| "total": 158.94455034498947, |
| "count": 105928, |
| "is_parallel": true, |
| "self": 31.719247934006717, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 127.22530241098275, |
| "count": 847424, |
| "is_parallel": true, |
| "self": 127.22530241098275 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1131.0432022169882, |
| "count": 105929, |
| "self": 3.143967183956647, |
| "children": { |
| "process_trajectory": { |
| "total": 201.6917680990341, |
| "count": 105929, |
| "self": 201.34088945203393, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.35087864700017235, |
| "count": 3, |
| "self": 0.35087864700017235 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 926.2074669339975, |
| "count": 669, |
| "self": 512.9651844069963, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 413.2422825270012, |
| "count": 38739, |
| "self": 413.2422825270012 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1680003808578476e-06, |
| "count": 1, |
| "self": 1.1680003808578476e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.1320373959997596, |
| "count": 1, |
| "self": 0.002061433000562829, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.12997596299919678, |
| "count": 1, |
| "self": 0.12997596299919678 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
