| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3393213450908661, |
| "min": 0.3314994275569916, |
| "max": 1.379373550415039, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10049.3408203125, |
| "min": 10008.630859375, |
| "max": 39019.71875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989933.0, |
| "min": 29952.0, |
| "max": 989933.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989933.0, |
| "min": 29952.0, |
| "max": 989933.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6254141330718994, |
| "min": -0.08404293656349182, |
| "max": 0.6912244558334351, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 180.74468994140625, |
| "min": -20.338390350341797, |
| "max": 203.21998596191406, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.02734558656811714, |
| "min": -0.02242613397538662, |
| "max": 0.4648740589618683, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 7.90287446975708, |
| "min": -5.9877777099609375, |
| "max": 102.73716735839844, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06841825248838398, |
| "min": 0.06641222656305348, |
| "max": 0.07352544943484582, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9578555348373757, |
| "min": 0.4401610603170662, |
| "max": 1.0786804384260904, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016256701561533624, |
| "min": 0.002270949388138241, |
| "max": 0.016508740748880278, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.22759382186147073, |
| "min": 0.022709493881382412, |
| "max": 0.2318545042265517, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.4898546462714276e-06, |
| "min": 7.4898546462714276e-06, |
| "max": 0.00029514240161919995, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010485796504779999, |
| "min": 0.00010485796504779999, |
| "max": 0.0035089250303584, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10249658571428573, |
| "min": 0.10249658571428573, |
| "max": 0.19838080000000002, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4349522000000001, |
| "min": 1.1902848000000001, |
| "max": 2.5696416, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002594089128571429, |
| "min": 0.0002594089128571429, |
| "max": 0.009838241919999999, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00363172478, |
| "min": 0.00363172478, |
| "max": 0.11698719584000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.01445481926202774, |
| "min": 0.01445481926202774, |
| "max": 0.5669408440589905, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.20236746966838837, |
| "min": 0.20236746966838837, |
| "max": 3.4016449451446533, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 285.0857142857143, |
| "min": 273.0093457943925, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29934.0, |
| "min": 15984.0, |
| "max": 33015.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.697030171470822, |
| "min": -1.0000000521540642, |
| "max": 1.7269906436450013, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 179.88519817590714, |
| "min": -30.24240168184042, |
| "max": 184.78799887001514, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.697030171470822, |
| "min": -1.0000000521540642, |
| "max": 1.7269906436450013, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 179.88519817590714, |
| "min": -30.24240168184042, |
| "max": 184.78799887001514, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04323365747651858, |
| "min": 0.04323365747651858, |
| "max": 11.171785168349743, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.58276769251097, |
| "min": 4.501126918883529, |
| "max": 178.7485626935959, |
| "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": "1727570619", |
| "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", |
| "command_line_arguments": "venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --resume", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.4.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1727572792" |
| }, |
| "total": 2173.1502576000003, |
| "count": 1, |
| "self": 0.4818422999996983, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01389500000004773, |
| "count": 1, |
| "self": 0.01389500000004773 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2172.6545203000005, |
| "count": 1, |
| "self": 1.5007186000343609, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.388296800000262, |
| "count": 1, |
| "self": 1.388296800000262 |
| }, |
| "TrainerController.advance": { |
| "total": 2169.6940161999664, |
| "count": 64084, |
| "self": 1.4004572000094413, |
| "children": { |
| "env_step": { |
| "total": 1451.9032732999935, |
| "count": 64084, |
| "self": 1339.2555544999796, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 111.717396799972, |
| "count": 64084, |
| "self": 4.25997569997935, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 107.45742109999264, |
| "count": 62432, |
| "self": 107.45742109999264 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9303220000419969, |
| "count": 64084, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2169.356929600043, |
| "count": 64084, |
| "is_parallel": true, |
| "self": 931.6386182001056, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019157000001541746, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005667000004905276, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001348999999663647, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001348999999663647 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.03984710000031555, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002482999998392188, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00021070000002509914, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00021070000002509914 |
| }, |
| "communicator.exchange": { |
| "total": 0.03852080000024216, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03852080000024216 |
| }, |
| "steps_from_proto": { |
| "total": 0.0008673000002090703, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00026889999890045146, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0005984000013086188, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0005984000013086188 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1237.7183113999372, |
| "count": 64083, |
| "is_parallel": true, |
| "self": 17.496068099939748, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 17.851628199996867, |
| "count": 64083, |
| "is_parallel": true, |
| "self": 17.851628199996867 |
| }, |
| "communicator.exchange": { |
| "total": 1148.1017410999953, |
| "count": 64083, |
| "is_parallel": true, |
| "self": 1148.1017410999953 |
| }, |
| "steps_from_proto": { |
| "total": 54.268874000005326, |
| "count": 64083, |
| "is_parallel": true, |
| "self": 14.00552580009753, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 40.263348199907796, |
| "count": 512664, |
| "is_parallel": true, |
| "self": 40.263348199907796 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 716.3902856999634, |
| "count": 64084, |
| "self": 3.2933098999124013, |
| "children": { |
| "process_trajectory": { |
| "total": 98.82236180005157, |
| "count": 64084, |
| "self": 98.51106890005167, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3112928999998985, |
| "count": 2, |
| "self": 0.3112928999998985 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 614.2746139999995, |
| "count": 454, |
| "self": 229.39425380004286, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 384.8803601999566, |
| "count": 22755, |
| "self": 384.8803601999566 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 7.999997251317836e-07, |
| "count": 1, |
| "self": 7.999997251317836e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07148789999973815, |
| "count": 1, |
| "self": 0.009067400000276393, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.062420499999461754, |
| "count": 1, |
| "self": 0.062420499999461754 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
