| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.475240021944046, |
| "min": 0.46541517972946167, |
| "max": 1.4633564949035645, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 14173.55859375, |
| "min": 13962.455078125, |
| "max": 44392.3828125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989895.0, |
| "min": 29895.0, |
| "max": 989895.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989895.0, |
| "min": 29895.0, |
| "max": 989895.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5235245227813721, |
| "min": -0.2340911477804184, |
| "max": 0.5236735939979553, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 143.96923828125, |
| "min": -55.4796028137207, |
| "max": 143.96923828125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.03888088837265968, |
| "min": -0.018090147525072098, |
| "max": 0.2799306809902191, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 10.692244529724121, |
| "min": -4.75770902633667, |
| "max": 73.06190490722656, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06962337272956834, |
| "min": 0.06403613343210299, |
| "max": 0.07349723073442875, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9747272182139568, |
| "min": 0.5656785967585228, |
| "max": 1.0621262683793355, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01322473961530098, |
| "min": 0.0007025245559779764, |
| "max": 0.022468483257052, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.18514635461421372, |
| "min": 0.006322721003801788, |
| "max": 0.314558765598728, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.407761816492854e-06, |
| "min": 7.407761816492854e-06, |
| "max": 0.00029499525166825, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010370866543089995, |
| "min": 0.00010370866543089995, |
| "max": 0.0036331156889614995, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10246922142857144, |
| "min": 0.10246922142857144, |
| "max": 0.19833175, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4345691000000003, |
| "min": 1.4345691000000003, |
| "max": 2.6110385000000007, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025667522071428565, |
| "min": 0.00025667522071428565, |
| "max": 0.009833341825000001, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003593453089999999, |
| "min": 0.003593453089999999, |
| "max": 0.12112274615000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010324850678443909, |
| "min": 0.010324850678443909, |
| "max": 0.3980882167816162, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.14454790949821472, |
| "min": 0.14454790949821472, |
| "max": 3.1847057342529297, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 362.3333333333333, |
| "min": 342.3, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29349.0, |
| "min": 16821.0, |
| "max": 32123.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5388740566961558, |
| "min": -0.9999806972280625, |
| "max": 1.5910244228111372, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 124.64879859238863, |
| "min": -31.998801663517952, |
| "max": 143.19219805300236, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5388740566961558, |
| "min": -0.9999806972280625, |
| "max": 1.5910244228111372, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 124.64879859238863, |
| "min": -31.998801663517952, |
| "max": 143.19219805300236, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.03878415141177053, |
| "min": 0.03878415141177053, |
| "max": 7.534700820015536, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.141516264353413, |
| "min": 3.141516264353413, |
| "max": 135.62461476027966, |
| "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": "1674052936", |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
| "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": "1674054947" |
| }, |
| "total": 2011.787828901, |
| "count": 1, |
| "self": 0.3963621290001811, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10353333900002326, |
| "count": 1, |
| "self": 0.10353333900002326 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2011.2879334329998, |
| "count": 1, |
| "self": 1.1178473749951081, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.0697630520000985, |
| "count": 1, |
| "self": 6.0697630520000985 |
| }, |
| "TrainerController.advance": { |
| "total": 2004.0146495820045, |
| "count": 63828, |
| "self": 1.1605653400238225, |
| "children": { |
| "env_step": { |
| "total": 1367.1529542059798, |
| "count": 63828, |
| "self": 1269.5356720280367, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 96.92909705092643, |
| "count": 63828, |
| "self": 4.049075117918164, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 92.88002193300827, |
| "count": 62560, |
| "self": 31.32916417103138, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 61.550857761976886, |
| "count": 62560, |
| "self": 61.550857761976886 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.6881851270165953, |
| "count": 63828, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2007.6760073899711, |
| "count": 63828, |
| "is_parallel": true, |
| "self": 830.2577266800017, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0018089249999775348, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005876300001546042, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012212949998229305, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012212949998229305 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.050259611000001314, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005057099999703496, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004216110000925255, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004216110000925255 |
| }, |
| "communicator.exchange": { |
| "total": 0.04782815799990203, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04782815799990203 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015041320000364067, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00039199200000439305, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011121400000320136, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011121400000320136 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1177.4182807099694, |
| "count": 63827, |
| "is_parallel": true, |
| "self": 27.022396464875783, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 21.231541364049235, |
| "count": 63827, |
| "is_parallel": true, |
| "self": 21.231541364049235 |
| }, |
| "communicator.exchange": { |
| "total": 1035.0354641479844, |
| "count": 63827, |
| "is_parallel": true, |
| "self": 1035.0354641479844 |
| }, |
| "steps_from_proto": { |
| "total": 94.12887873305999, |
| "count": 63827, |
| "is_parallel": true, |
| "self": 20.341070800982152, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 73.78780793207784, |
| "count": 510616, |
| "is_parallel": true, |
| "self": 73.78780793207784 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 635.7011300360009, |
| "count": 63828, |
| "self": 2.0364603400880696, |
| "children": { |
| "process_trajectory": { |
| "total": 138.81790026991234, |
| "count": 63828, |
| "self": 138.63125504091272, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.18664522899962321, |
| "count": 2, |
| "self": 0.18664522899962321 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 494.8467694260005, |
| "count": 451, |
| "self": 183.84266522800044, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 311.00410419800005, |
| "count": 22833, |
| "self": 311.00410419800005 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.609999895270448e-07, |
| "count": 1, |
| "self": 8.609999895270448e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0856725630001165, |
| "count": 1, |
| "self": 0.001478554999721382, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08419400800039512, |
| "count": 1, |
| "self": 0.08419400800039512 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
