| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5513584613800049, |
| "min": 0.5301269292831421, |
| "max": 1.4103143215179443, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 16593.68359375, |
| "min": 15869.8798828125, |
| "max": 42783.296875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989925.0, |
| "min": 29952.0, |
| "max": 989925.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989925.0, |
| "min": 29952.0, |
| "max": 989925.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.3097856044769287, |
| "min": -0.1174902692437172, |
| "max": 0.34394770860671997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 80.85404205322266, |
| "min": -28.315155029296875, |
| "max": 89.08245849609375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.003238753881305456, |
| "min": -0.004479636438190937, |
| "max": 0.4609505832195282, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 0.8453147411346436, |
| "min": -1.1602258682250977, |
| "max": 109.24528503417969, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07075192811455401, |
| "min": 0.06475120262761831, |
| "max": 0.07397103929050705, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9905269936037561, |
| "min": 0.5177972750335493, |
| "max": 1.0640958740744584, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.011359723112989396, |
| "min": 8.4462587378174e-05, |
| "max": 0.013660703793482585, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.15903612358185154, |
| "min": 0.0011824762232944361, |
| "max": 0.1912498531087562, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.5776474741499995e-06, |
| "min": 7.5776474741499995e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0001060870646381, |
| "min": 0.0001060870646381, |
| "max": 0.0033816509727831005, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10252585000000003, |
| "min": 0.10252585000000003, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4353619000000004, |
| "min": 1.3886848, |
| "max": 2.5272169, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00026233241500000007, |
| "min": 0.00026233241500000007, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003672653810000001, |
| "min": 0.003672653810000001, |
| "max": 0.11274896831, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012139945290982723, |
| "min": 0.012139945290982723, |
| "max": 0.5525259375572205, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16995923221111298, |
| "min": 0.16995923221111298, |
| "max": 3.8676815032958984, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 536.7884615384615, |
| "min": 509.89830508474574, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27913.0, |
| "min": 15984.0, |
| "max": 32513.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.1552905402374718, |
| "min": -1.0000000521540642, |
| "max": 1.2866542166319943, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 61.230398632586, |
| "min": -31.986801609396935, |
| "max": 75.91259878128767, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.1552905402374718, |
| "min": -1.0000000521540642, |
| "max": 1.2866542166319943, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 61.230398632586, |
| "min": -31.986801609396935, |
| "max": 75.91259878128767, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.06852846518312669, |
| "min": 0.06765543631454575, |
| "max": 11.538302543573081, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.6320086547057144, |
| "min": 3.6320086547057144, |
| "max": 184.6128406971693, |
| "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": "1762986320", |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", |
| "command_line_arguments": "/usr/local/envs/myenv/bin/mlagents-learn ml-agents/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": "1762988467" |
| }, |
| "total": 2146.86322877, |
| "count": 1, |
| "self": 0.4776796930004821, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0185774839997066, |
| "count": 1, |
| "self": 0.0185774839997066 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2146.366971593, |
| "count": 1, |
| "self": 1.3853013818011277, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.0133637799999633, |
| "count": 1, |
| "self": 2.0133637799999633 |
| }, |
| "TrainerController.advance": { |
| "total": 2142.8935776331996, |
| "count": 63345, |
| "self": 1.402171922378784, |
| "children": { |
| "env_step": { |
| "total": 1479.4567893518406, |
| "count": 63345, |
| "self": 1328.3619882506196, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 150.2416580240988, |
| "count": 63345, |
| "self": 4.720288288088341, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 145.52136973601046, |
| "count": 62560, |
| "self": 145.52136973601046 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8531430771222404, |
| "count": 63345, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2140.0175137501437, |
| "count": 63345, |
| "is_parallel": true, |
| "self": 929.8254902861913, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002195013999880757, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007515149991377257, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014434990007430315, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014434990007430315 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0796552110000448, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005211519996919378, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004921590002595622, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004921590002595622 |
| }, |
| "communicator.exchange": { |
| "total": 0.07704694599988215, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.07704694599988215 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015949540002111462, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003674790004879469, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012274749997231993, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012274749997231993 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1210.1920234639524, |
| "count": 63344, |
| "is_parallel": true, |
| "self": 33.69369787954429, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.894961115101978, |
| "count": 63344, |
| "is_parallel": true, |
| "self": 23.894961115101978 |
| }, |
| "communicator.exchange": { |
| "total": 1041.3642319690657, |
| "count": 63344, |
| "is_parallel": true, |
| "self": 1041.3642319690657 |
| }, |
| "steps_from_proto": { |
| "total": 111.23913250024043, |
| "count": 63344, |
| "is_parallel": true, |
| "self": 23.43528195717181, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 87.80385054306862, |
| "count": 506752, |
| "is_parallel": true, |
| "self": 87.80385054306862 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 662.0346163589802, |
| "count": 63345, |
| "self": 2.5758351188965207, |
| "children": { |
| "process_trajectory": { |
| "total": 123.7848195550805, |
| "count": 63345, |
| "self": 123.55281150508108, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.23200804999942193, |
| "count": 2, |
| "self": 0.23200804999942193 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 535.6739616850032, |
| "count": 442, |
| "self": 299.10433934309594, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 236.56962234190723, |
| "count": 22788, |
| "self": 236.56962234190723 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.449997039861046e-07, |
| "count": 1, |
| "self": 8.449997039861046e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07472795299963764, |
| "count": 1, |
| "self": 0.0009888280001177918, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07373912499951985, |
| "count": 1, |
| "self": 0.07373912499951985 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
