| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.8323522210121155, |
| "min": 0.8323522210121155, |
| "max": 1.4688894748687744, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 24930.61328125, |
| "min": 24930.61328125, |
| "max": 44560.23046875, |
| "count": 3 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 89953.0, |
| "min": 29952.0, |
| "max": 89953.0, |
| "count": 3 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 89953.0, |
| "min": 29952.0, |
| "max": 89953.0, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.09592054784297943, |
| "min": -0.09592054784297943, |
| "max": 0.03983438014984131, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -23.116851806640625, |
| "min": -23.116851806640625, |
| "max": 9.44074821472168, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.17069073021411896, |
| "min": 0.12402097135782242, |
| "max": 0.22428525984287262, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 41.13646697998047, |
| "min": 29.39297103881836, |
| "max": 53.828460693359375, |
| "count": 3 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06733157473897167, |
| "min": 0.06733157473897167, |
| "max": 0.07045983251055002, |
| "count": 3 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.7406473221286883, |
| "min": 0.4932188275738501, |
| "max": 0.7406473221286883, |
| "count": 3 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0009421695563272336, |
| "min": 0.0009421695563272336, |
| "max": 0.004145141092810184, |
| "count": 3 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.01036386511959957, |
| "min": 0.009659244228060963, |
| "max": 0.02901598764967129, |
| "count": 3 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.818116484872727e-05, |
| "min": 7.818116484872727e-05, |
| "max": 0.0002515063018788571, |
| "count": 3 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.000859992813336, |
| "min": 0.000859992813336, |
| "max": 0.0017605441131519997, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.12606036363636364, |
| "min": 0.12606036363636364, |
| "max": 0.1838354285714286, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.3866640000000001, |
| "min": 1.2392880000000002, |
| "max": 1.3866640000000001, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.002613430327272728, |
| "min": 0.002613430327272728, |
| "max": 0.008385159314285713, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.028747733600000006, |
| "min": 0.028747733600000006, |
| "max": 0.058696115199999996, |
| "count": 3 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.12022758275270462, |
| "min": 0.12022758275270462, |
| "max": 0.3930082619190216, |
| "count": 3 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 1.3225034475326538, |
| "min": 1.3225034475326538, |
| "max": 2.7510578632354736, |
| "count": 3 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 987.0909090909091, |
| "min": 987.0909090909091, |
| "max": 999.0, |
| "count": 3 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32574.0, |
| "min": 15984.0, |
| "max": 32574.0, |
| "count": 3 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.9274182326414369, |
| "min": -1.0000000521540642, |
| "max": -0.9274182326414369, |
| "count": 3 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -30.604801677167416, |
| "min": -30.604801677167416, |
| "max": -16.000000834465027, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.9274182326414369, |
| "min": -1.0000000521540642, |
| "max": -0.9274182326414369, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -30.604801677167416, |
| "min": -30.604801677167416, |
| "max": -16.000000834465027, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 1.3880127560008655, |
| "min": 1.3880127560008655, |
| "max": 7.517998921684921, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 45.804420948028564, |
| "min": 45.804420948028564, |
| "max": 120.28798274695873, |
| "count": 3 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 3 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 3 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1677257043", |
| "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": "1.22.4", |
| "end_time_seconds": "1677257259" |
| }, |
| "total": 216.592328935, |
| "count": 1, |
| "self": 0.48901486199997635, |
| "children": { |
| "run_training.setup": { |
| "total": 0.1088189990000501, |
| "count": 1, |
| "self": 0.1088189990000501 |
| }, |
| "TrainerController.start_learning": { |
| "total": 215.99449507399999, |
| "count": 1, |
| "self": 0.1367197060016565, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 9.11554398300001, |
| "count": 1, |
| "self": 9.11554398300001 |
| }, |
| "TrainerController.advance": { |
| "total": 206.6333847529982, |
| "count": 6264, |
| "self": 0.1507085469962135, |
| "children": { |
| "env_step": { |
| "total": 129.7133109340047, |
| "count": 6264, |
| "self": 117.63257043099958, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 11.988092498002857, |
| "count": 6264, |
| "self": 0.5082369689985171, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 11.47985552900434, |
| "count": 6258, |
| "self": 3.9001356640038694, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 7.57971986500047, |
| "count": 6258, |
| "self": 7.57971986500047 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.09264800500227466, |
| "count": 6264, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 215.49129896300167, |
| "count": 6264, |
| "is_parallel": true, |
| "self": 109.81543781099987, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005103849000022365, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.002761932999931105, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0023419160000912598, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0023419160000912598 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05162206199997854, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005609809999214121, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00048644900005001546, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00048644900005001546 |
| }, |
| "communicator.exchange": { |
| "total": 0.04863985499997625, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04863985499997625 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019347770000308628, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005720340001289514, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013627429999019114, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013627429999019114 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 105.6758611520018, |
| "count": 6263, |
| "is_parallel": true, |
| "self": 3.2793998159993407, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 2.5232583559973705, |
| "count": 6263, |
| "is_parallel": true, |
| "self": 2.5232583559973705 |
| }, |
| "communicator.exchange": { |
| "total": 89.83286614800363, |
| "count": 6263, |
| "is_parallel": true, |
| "self": 89.83286614800363 |
| }, |
| "steps_from_proto": { |
| "total": 10.040336832001458, |
| "count": 6263, |
| "is_parallel": true, |
| "self": 2.4256375919957804, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 7.614699240005677, |
| "count": 50104, |
| "is_parallel": true, |
| "self": 7.614699240005677 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 76.76936527199729, |
| "count": 6264, |
| "self": 0.196145302994978, |
| "children": { |
| "process_trajectory": { |
| "total": 16.45395645200216, |
| "count": 6264, |
| "self": 16.45395645200216 |
| }, |
| "_update_policy": { |
| "total": 60.11926351700015, |
| "count": 30, |
| "self": 23.195737322997616, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 36.923526194002534, |
| "count": 2286, |
| "self": 36.923526194002534 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.930001058615744e-07, |
| "count": 1, |
| "self": 8.930001058615744e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10884573900000305, |
| "count": 1, |
| "self": 0.0014978359999986424, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10734790300000441, |
| "count": 1, |
| "self": 0.10734790300000441 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
