| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.8995862007141113, |
| "min": 0.8995862007141113, |
| "max": 1.454206109046936, |
| "count": 6 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 26901.2265625, |
| "min": 26901.2265625, |
| "max": 44114.796875, |
| "count": 6 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 179922.0, |
| "min": 29882.0, |
| "max": 179922.0, |
| "count": 6 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 179922.0, |
| "min": 29882.0, |
| "max": 179922.0, |
| "count": 6 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.08334647864103317, |
| "min": -0.09363283962011337, |
| "max": 0.028996169567108154, |
| "count": 6 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -20.086502075195312, |
| "min": -22.565513610839844, |
| "max": 6.872092247009277, |
| "count": 6 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.06044967100024223, |
| "min": 0.06044967100024223, |
| "max": 0.319549560546875, |
| "count": 6 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 14.568370819091797, |
| "min": 14.568370819091797, |
| "max": 75.73324584960938, |
| "count": 6 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06991601909629647, |
| "min": 0.0669309777444603, |
| "max": 0.07281179393442894, |
| "count": 6 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.908908248251854, |
| "min": 0.5096825575410026, |
| "max": 0.908908248251854, |
| "count": 6 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0012823803997391065, |
| "min": 0.00018725260363460143, |
| "max": 0.006188299495180815, |
| "count": 6 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.016670945196608385, |
| "min": 0.0024342838472498187, |
| "max": 0.04331809646626571, |
| "count": 6 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 5.151458282849999e-05, |
| "min": 5.151458282849999e-05, |
| "max": 0.00027575315093942855, |
| "count": 6 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0006696895767704999, |
| "min": 0.0006696895767704999, |
| "max": 0.0025619672460110003, |
| "count": 6 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1171715, |
| "min": 0.1171715, |
| "max": 0.19191771428571427, |
| "count": 6 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5232295, |
| "min": 1.343424, |
| "max": 1.9539890000000002, |
| "count": 6 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0017254328500000003, |
| "min": 0.0017254328500000003, |
| "max": 0.009192579657142857, |
| "count": 6 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.022430627050000006, |
| "min": 0.022430627050000006, |
| "max": 0.08542350110000001, |
| "count": 6 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.052695635706186295, |
| "min": 0.052695635706186295, |
| "max": 0.39450564980506897, |
| "count": 6 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.6850432753562927, |
| "min": 0.6850432753562927, |
| "max": 2.7615394592285156, |
| "count": 6 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 958.0, |
| "min": 958.0, |
| "max": 999.0, |
| "count": 6 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32572.0, |
| "min": 16809.0, |
| "max": 32572.0, |
| "count": 6 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.8363636860793288, |
| "min": -0.9998875521123409, |
| "max": -0.7836485349319198, |
| "count": 6 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -27.600001640617847, |
| "min": -31.99640166759491, |
| "max": -14.825000911951065, |
| "count": 6 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.8363636860793288, |
| "min": -0.9998875521123409, |
| "max": -0.7836485349319198, |
| "count": 6 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -27.600001640617847, |
| "min": -31.99640166759491, |
| "max": -14.825000911951065, |
| "count": 6 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.5387352874333208, |
| "min": 0.5387352874333208, |
| "max": 7.7710857483394005, |
| "count": 6 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 17.778264485299587, |
| "min": 17.778264485299587, |
| "max": 132.1084577217698, |
| "count": 6 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 6 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 6 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1759494890", |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", |
| "command_line_arguments": "/root/.local/share/mamba/envs/u10/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND1 --no-graphics", |
| "mlagents_version": "1.1.0", |
| "mlagents_envs_version": "1.1.0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1759495475" |
| }, |
| "total": 585.1926151550001, |
| "count": 1, |
| "self": 0.5460800729997572, |
| "children": { |
| "run_training.setup": { |
| "total": 0.04039032899981976, |
| "count": 1, |
| "self": 0.04039032899981976 |
| }, |
| "TrainerController.start_learning": { |
| "total": 584.6061447530005, |
| "count": 1, |
| "self": 0.4329372680385859, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.2851930990000255, |
| "count": 1, |
| "self": 3.2851930990000255 |
| }, |
| "TrainerController.advance": { |
| "total": 580.5869333149617, |
| "count": 12606, |
| "self": 0.4788515179084243, |
| "children": { |
| "env_step": { |
| "total": 379.204233546036, |
| "count": 12606, |
| "self": 347.5815240700663, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 31.359648098981324, |
| "count": 12606, |
| "self": 1.3449598949473511, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 30.014688204033973, |
| "count": 12569, |
| "self": 30.014688204033973 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.2630613769883894, |
| "count": 12606, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 583.1013726920082, |
| "count": 12606, |
| "is_parallel": true, |
| "self": 269.2788808590044, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.004011348999938491, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.001448401000288868, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002562947999649623, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002562947999649623 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.13084931000003053, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006335590001071978, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0011069160000261036, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0011069160000261036 |
| }, |
| "communicator.exchange": { |
| "total": 0.1226994690000538, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.1226994690000538 |
| }, |
| "steps_from_proto": { |
| "total": 0.0064093659998434305, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004196439995212131, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.005989722000322217, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.005989722000322217 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 313.8224918330038, |
| "count": 12605, |
| "is_parallel": true, |
| "self": 9.168796041906262, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 5.948099299041587, |
| "count": 12605, |
| "is_parallel": true, |
| "self": 5.948099299041587 |
| }, |
| "communicator.exchange": { |
| "total": 269.25932263704635, |
| "count": 12605, |
| "is_parallel": true, |
| "self": 269.25932263704635 |
| }, |
| "steps_from_proto": { |
| "total": 29.446273855009622, |
| "count": 12605, |
| "is_parallel": true, |
| "self": 6.432408007217873, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 23.01386584779175, |
| "count": 100840, |
| "is_parallel": true, |
| "self": 23.01386584779175 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 200.90384825101728, |
| "count": 12606, |
| "self": 0.6625152340188833, |
| "children": { |
| "process_trajectory": { |
| "total": 29.751444521000394, |
| "count": 12606, |
| "self": 29.751444521000394 |
| }, |
| "_update_policy": { |
| "total": 170.489888495998, |
| "count": 76, |
| "self": 69.11183417899565, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 101.37805431700235, |
| "count": 4563, |
| "self": 101.37805431700235 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.630002750782296e-07, |
| "count": 1, |
| "self": 9.630002750782296e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.301080107999951, |
| "count": 1, |
| "self": 0.005557440000302449, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.29552266799964855, |
| "count": 1, |
| "self": 0.29552266799964855 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
