| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.18104781210422516, |
| "min": 0.17951814830303192, |
| "max": 1.505823016166687, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5469.09228515625, |
| "min": 5339.06396484375, |
| "max": 45680.6484375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999991.0, |
| "min": 29952.0, |
| "max": 2999991.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999991.0, |
| "min": 29952.0, |
| "max": 2999991.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7798470854759216, |
| "min": -0.09319421648979187, |
| "max": 0.8462048172950745, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 233.95413208007812, |
| "min": -22.459806442260742, |
| "max": 254.70765686035156, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.004614067263901234, |
| "min": -0.03470351919531822, |
| "max": 0.22959883511066437, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.3842201232910156, |
| "min": -10.064020156860352, |
| "max": 55.33332061767578, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06855525530274556, |
| "min": 0.0639820255427843, |
| "max": 0.07459573431042983, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9597735742384378, |
| "min": 0.5048335795575115, |
| "max": 1.0832571756724134, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015200539068883048, |
| "min": 9.864793461255642e-05, |
| "max": 0.016334991009633537, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21280754696436266, |
| "min": 0.00138107108457579, |
| "max": 0.24502486514450306, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5063352122071473e-06, |
| "min": 1.5063352122071473e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.1088692970900062e-05, |
| "min": 2.1088692970900062e-05, |
| "max": 0.0039694185768605, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10050207857142857, |
| "min": 0.10050207857142857, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4070291, |
| "min": 1.3962282666666668, |
| "max": 2.7825643333333336, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.015764928571443e-05, |
| "min": 6.015764928571443e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.000842207090000002, |
| "min": 0.000842207090000002, |
| "max": 0.13232163605000002, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.00476462347432971, |
| "min": 0.004640344996005297, |
| "max": 0.38075801730155945, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.06670472770929337, |
| "min": 0.06496483087539673, |
| "max": 2.6653060913085938, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 225.6865671641791, |
| "min": 212.6595744680851, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30242.0, |
| "min": 15984.0, |
| "max": 32793.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.772787865477078, |
| "min": -1.0000000521540642, |
| "max": 1.7873404152849888, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 234.00799824297428, |
| "min": -30.99780163168907, |
| "max": 252.0149985551834, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.772787865477078, |
| "min": -1.0000000521540642, |
| "max": 1.7873404152849888, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 234.00799824297428, |
| "min": -30.99780163168907, |
| "max": 252.0149985551834, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.011287698691169433, |
| "min": 0.01075812402758863, |
| "max": 7.786096006631851, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.489976227234365, |
| "min": 1.4349761332432536, |
| "max": 124.57753610610962, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1767538493", |
| "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 --force --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": "1767549895" |
| }, |
| "total": 11401.169093854001, |
| "count": 1, |
| "self": 1.2096521699986624, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03249792200040247, |
| "count": 1, |
| "self": 0.03249792200040247 |
| }, |
| "TrainerController.start_learning": { |
| "total": 11399.926943762002, |
| "count": 1, |
| "self": 7.437284659030411, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.2962505119994603, |
| "count": 1, |
| "self": 2.2962505119994603 |
| }, |
| "TrainerController.advance": { |
| "total": 11390.075336044973, |
| "count": 195103, |
| "self": 8.177962583367844, |
| "children": { |
| "env_step": { |
| "total": 8017.608978907674, |
| "count": 195103, |
| "self": 7511.194270820328, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 502.1649875440744, |
| "count": 195103, |
| "self": 22.47163748555795, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 479.69335005851644, |
| "count": 187564, |
| "self": 479.69335005851644 |
| } |
| } |
| }, |
| "workers": { |
| "total": 4.249720543271906, |
| "count": 195103, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 11372.56929772392, |
| "count": 195103, |
| "is_parallel": true, |
| "self": 4444.114493861551, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0022354740012815455, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007344810001086444, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015009930011729011, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015009930011729011 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06560824200096249, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006707870015816297, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005653389998769853, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005653389998769853 |
| }, |
| "communicator.exchange": { |
| "total": 0.06236436499966658, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.06236436499966658 |
| }, |
| "steps_from_proto": { |
| "total": 0.002007750999837299, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004386509990581544, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015691000007791445, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015691000007791445 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 6928.454803862369, |
| "count": 195102, |
| "is_parallel": true, |
| "self": 143.21637205613115, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 96.63644722187564, |
| "count": 195102, |
| "is_parallel": true, |
| "self": 96.63644722187564 |
| }, |
| "communicator.exchange": { |
| "total": 6235.939923153717, |
| "count": 195102, |
| "is_parallel": true, |
| "self": 6235.939923153717 |
| }, |
| "steps_from_proto": { |
| "total": 452.6620614306448, |
| "count": 195102, |
| "is_parallel": true, |
| "self": 90.69724872002371, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 361.9648127106211, |
| "count": 1560816, |
| "is_parallel": true, |
| "self": 361.9648127106211 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 3364.2883945539306, |
| "count": 195103, |
| "self": 14.801266675814986, |
| "children": { |
| "process_trajectory": { |
| "total": 514.329369602081, |
| "count": 195103, |
| "self": 513.5730235260817, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.7563460759993177, |
| "count": 6, |
| "self": 0.7563460759993177 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 2835.1577582760347, |
| "count": 1396, |
| "self": 1120.1209886020424, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 1715.0367696739922, |
| "count": 68406, |
| "self": 1715.0367696739922 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.2140008038841188e-06, |
| "count": 1, |
| "self": 1.2140008038841188e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.11807133199909003, |
| "count": 1, |
| "self": 0.007232233001559507, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.11083909899753053, |
| "count": 1, |
| "self": 0.11083909899753053 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
