| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2676398754119873, |
| "min": 0.24435018002986908, |
| "max": 1.458091139793396, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8131.9697265625, |
| "min": 7310.95751953125, |
| "max": 44232.65234375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989973.0, |
| "min": 29952.0, |
| "max": 989973.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989973.0, |
| "min": 29952.0, |
| "max": 989973.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6546875238418579, |
| "min": -0.0858505517244339, |
| "max": 0.7069087624549866, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 185.2765655517578, |
| "min": -20.775833129882812, |
| "max": 211.36572265625, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.02567695826292038, |
| "min": 0.002442799974232912, |
| "max": 0.29490306973457336, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 7.2665791511535645, |
| "min": 0.7303972244262695, |
| "max": 71.07164001464844, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06423122331380866, |
| "min": 0.06401542375706845, |
| "max": 0.07189476626397764, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.8992371263933213, |
| "min": 0.5032633638478435, |
| "max": 1.0684723953377482, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01730408791696564, |
| "min": 0.0005118279006379746, |
| "max": 0.018183937722312273, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.24225723083751896, |
| "min": 0.005630106907017721, |
| "max": 0.2545751281123718, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.31636898981429e-06, |
| "min": 7.31636898981429e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010242916585740006, |
| "min": 0.00010242916585740006, |
| "max": 0.0033786485737839, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10243875714285713, |
| "min": 0.10243875714285713, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4341426, |
| "min": 1.3886848, |
| "max": 2.5272634999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002536318385714288, |
| "min": 0.0002536318385714288, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035508457400000035, |
| "min": 0.0035508457400000035, |
| "max": 0.11264898838999998, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.0163896381855011, |
| "min": 0.015789085999131203, |
| "max": 0.48644518852233887, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.22945493459701538, |
| "min": 0.22784022986888885, |
| "max": 3.405116319656372, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 284.0192307692308, |
| "min": 244.6, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29538.0, |
| "min": 15984.0, |
| "max": 33358.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6591295037950788, |
| "min": -1.0000000521540642, |
| "max": 1.7138696271660072, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 174.20859789848328, |
| "min": -29.390001744031906, |
| "max": 215.2311990186572, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6591295037950788, |
| "min": -1.0000000521540642, |
| "max": 1.7138696271660072, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 174.20859789848328, |
| "min": -29.390001744031906, |
| "max": 215.2311990186572, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04786284161687252, |
| "min": 0.04137930580855893, |
| "max": 8.93800566252321, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 5.025598369771615, |
| "min": 4.7574313473305665, |
| "max": 143.00809060037136, |
| "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": "1673508057", |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
| "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": "0.29.0.dev0", |
| "mlagents_envs_version": "0.29.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.8.1+cu102", |
| "numpy_version": "1.21.6", |
| "end_time_seconds": "1673510242" |
| }, |
| "total": 2185.233596528, |
| "count": 1, |
| "self": 0.42453163000027416, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10832081900002777, |
| "count": 1, |
| "self": 0.10832081900002777 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2184.700744079, |
| "count": 1, |
| "self": 1.347564030048943, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.156738388999884, |
| "count": 1, |
| "self": 6.156738388999884 |
| }, |
| "TrainerController.advance": { |
| "total": 2177.1095029289504, |
| "count": 64358, |
| "self": 1.5047958649506654, |
| "children": { |
| "env_step": { |
| "total": 1521.678020401022, |
| "count": 64358, |
| "self": 1412.7416569909735, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 108.0940331340239, |
| "count": 64358, |
| "self": 4.3643202360237865, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 103.72971289800012, |
| "count": 62549, |
| "self": 34.84671401795845, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 68.88299888004167, |
| "count": 62549, |
| "self": 68.88299888004167 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8423302760245406, |
| "count": 64358, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2179.829430234983, |
| "count": 64358, |
| "is_parallel": true, |
| "self": 871.8321961729848, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0016470770001433266, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005913869995310961, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0010556900006122305, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0010556900006122305 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04369800199992824, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004900470000848145, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004189609999230015, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004189609999230015 |
| }, |
| "communicator.exchange": { |
| "total": 0.04126533199996629, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04126533199996629 |
| }, |
| "steps_from_proto": { |
| "total": 0.001523661999954129, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000394608000306107, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001129053999648022, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001129053999648022 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1307.9972340619984, |
| "count": 64357, |
| "is_parallel": true, |
| "self": 28.11062186297636, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.33181062802032, |
| "count": 64357, |
| "is_parallel": true, |
| "self": 23.33181062802032 |
| }, |
| "communicator.exchange": { |
| "total": 1152.8494303549999, |
| "count": 64357, |
| "is_parallel": true, |
| "self": 1152.8494303549999 |
| }, |
| "steps_from_proto": { |
| "total": 103.70537121600182, |
| "count": 64357, |
| "is_parallel": true, |
| "self": 23.340232297089642, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 80.36513891891218, |
| "count": 514856, |
| "is_parallel": true, |
| "self": 80.36513891891218 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 653.9266866629778, |
| "count": 64358, |
| "self": 2.5824938159769317, |
| "children": { |
| "process_trajectory": { |
| "total": 145.48867960000575, |
| "count": 64358, |
| "self": 145.2939338420058, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19474575799995364, |
| "count": 2, |
| "self": 0.19474575799995364 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 505.8555132469951, |
| "count": 452, |
| "self": 195.80155579600932, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 310.05395745098576, |
| "count": 22833, |
| "self": 310.05395745098576 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0450003173900768e-06, |
| "count": 1, |
| "self": 1.0450003173900768e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08693768600005569, |
| "count": 1, |
| "self": 0.0013440230000014708, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08559366300005422, |
| "count": 1, |
| "self": 0.08559366300005422 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
