| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5167971253395081, |
| "min": 0.5167971253395081, |
| "max": 1.4433250427246094, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 15536.98828125, |
| "min": 15536.98828125, |
| "max": 43784.70703125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989983.0, |
| "min": 29952.0, |
| "max": 989983.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989983.0, |
| "min": 29952.0, |
| "max": 989983.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5022132396697998, |
| "min": -0.14150525629520416, |
| "max": 0.5022132396697998, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 140.11749267578125, |
| "min": -33.536746978759766, |
| "max": 140.11749267578125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.003702560206875205, |
| "min": -0.011717728339135647, |
| "max": 0.2295435070991516, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.0330142974853516, |
| "min": -3.0231738090515137, |
| "max": 54.40180969238281, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06860488394089598, |
| "min": 0.06441505321524187, |
| "max": 0.07304494783082713, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9604683751725437, |
| "min": 0.5006592064559321, |
| "max": 1.0743747338773593, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01639499163207975, |
| "min": 0.0003351879405584834, |
| "max": 0.01639499163207975, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2295298828491165, |
| "min": 0.004692631167818768, |
| "max": 0.2295298828491165, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.552040339828576e-06, |
| "min": 7.552040339828576e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010572856475760006, |
| "min": 0.00010572856475760006, |
| "max": 0.0034932553355815996, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10251731428571431, |
| "min": 0.10251731428571431, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4352424000000004, |
| "min": 1.3886848, |
| "max": 2.4853991000000004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002614796971428573, |
| "min": 0.0002614796971428573, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003660715760000002, |
| "min": 0.003660715760000002, |
| "max": 0.11645539816000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010885819792747498, |
| "min": 0.010279275476932526, |
| "max": 0.3817487359046936, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.15240147709846497, |
| "min": 0.14390985667705536, |
| "max": 2.6722412109375, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 336.6588235294118, |
| "min": 336.6588235294118, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28616.0, |
| "min": 15984.0, |
| "max": 32462.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5456682156114017, |
| "min": -1.0000000521540642, |
| "max": 1.546772488206625, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 131.38179832696915, |
| "min": -30.48240166902542, |
| "max": 131.38179832696915, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5456682156114017, |
| "min": -1.0000000521540642, |
| "max": 1.546772488206625, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 131.38179832696915, |
| "min": -30.48240166902542, |
| "max": 131.38179832696915, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.037740070685086884, |
| "min": 0.037740070685086884, |
| "max": 7.38467076793313, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.207906008232385, |
| "min": 3.15282974128786, |
| "max": 118.15473228693008, |
| "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": "1682301734", |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1682303866" |
| }, |
| "total": 2131.61389426, |
| "count": 1, |
| "self": 0.47860581599979923, |
| "children": { |
| "run_training.setup": { |
| "total": 0.11279454900000019, |
| "count": 1, |
| "self": 0.11279454900000019 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2131.022493895, |
| "count": 1, |
| "self": 1.4610299049973037, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.9181328669999402, |
| "count": 1, |
| "self": 3.9181328669999402 |
| }, |
| "TrainerController.advance": { |
| "total": 2125.5453520970027, |
| "count": 63600, |
| "self": 1.4689997799837329, |
| "children": { |
| "env_step": { |
| "total": 1494.4567739980398, |
| "count": 63600, |
| "self": 1386.3614530120362, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 107.20887278599525, |
| "count": 63600, |
| "self": 4.902446939019683, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 102.30642584697557, |
| "count": 62584, |
| "self": 102.30642584697557 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8864482000083171, |
| "count": 63600, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2126.2582959209517, |
| "count": 63600, |
| "is_parallel": true, |
| "self": 851.3763792939571, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0016756079999140638, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005529990000923135, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011226089998217503, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011226089998217503 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04862211399995431, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005903359999592794, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004814310000256228, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004814310000256228 |
| }, |
| "communicator.exchange": { |
| "total": 0.04595877199994902, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04595877199994902 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015915750000203843, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036731599993800046, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012242590000823839, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012242590000823839 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1274.8819166269946, |
| "count": 63599, |
| "is_parallel": true, |
| "self": 33.31224227694088, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.350891246025412, |
| "count": 63599, |
| "is_parallel": true, |
| "self": 23.350891246025412 |
| }, |
| "communicator.exchange": { |
| "total": 1122.1976996139954, |
| "count": 63599, |
| "is_parallel": true, |
| "self": 1122.1976996139954 |
| }, |
| "steps_from_proto": { |
| "total": 96.02108349003288, |
| "count": 63599, |
| "is_parallel": true, |
| "self": 20.413379306063916, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 75.60770418396896, |
| "count": 508792, |
| "is_parallel": true, |
| "self": 75.60770418396896 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 629.6195783189794, |
| "count": 63600, |
| "self": 2.6700187889814515, |
| "children": { |
| "process_trajectory": { |
| "total": 106.55987038099397, |
| "count": 63600, |
| "self": 106.28457949099334, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2752908900006332, |
| "count": 2, |
| "self": 0.2752908900006332 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 520.389689149004, |
| "count": 449, |
| "self": 334.7074270720268, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 185.68226207697717, |
| "count": 22776, |
| "self": 185.68226207697717 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.750001481734216e-07, |
| "count": 1, |
| "self": 9.750001481734216e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09797805100015466, |
| "count": 1, |
| "self": 0.0018610729998727038, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09611697800028196, |
| "count": 1, |
| "self": 0.09611697800028196 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
