| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.4314044415950775, |
| "min": 0.4314044415950775, |
| "max": 0.7790645360946655, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 12907.62109375, |
| "min": 7901.201171875, |
| "max": 23720.95703125, |
| "count": 17 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 393.8243243243243, |
| "min": 329.875, |
| "max": 636.0961538461538, |
| "count": 17 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29143.0, |
| "min": 2639.0, |
| "max": 33077.0, |
| "count": 17 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989985.0, |
| "min": 509915.0, |
| "max": 989985.0, |
| "count": 17 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989985.0, |
| "min": 509915.0, |
| "max": 989985.0, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4589470326900482, |
| "min": 0.2170439213514328, |
| "max": 0.5810307860374451, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 124.8335952758789, |
| "min": 17.7976016998291, |
| "max": 159.2024383544922, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.04644458368420601, |
| "min": -0.021390676498413086, |
| "max": 0.09362786263227463, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 12.632926940917969, |
| "min": -5.647138595581055, |
| "max": 25.747661590576172, |
| "count": 17 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.4492986406882604, |
| "min": 0.863696120106257, |
| "max": 1.6701249796897173, |
| "count": 17 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 108.69739805161953, |
| "min": 13.360999837517738, |
| "max": 136.36779829114676, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.4492986406882604, |
| "min": 0.863696120106257, |
| "max": 1.6701249796897173, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 108.69739805161953, |
| "min": 13.360999837517738, |
| "max": 136.36779829114676, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.051743122888728975, |
| "min": 0.047046523428563136, |
| "max": 0.16165042101727942, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.880734216654673, |
| "min": 0.7199835192877799, |
| "max": 8.40582189289853, |
| "count": 17 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06681355783144856, |
| "min": 0.06530414389573393, |
| "max": 0.07064831982073583, |
| "count": 17 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9353898096402798, |
| "min": 0.2648147810056495, |
| "max": 1.049596157660548, |
| "count": 17 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014727225579138446, |
| "min": 0.007457974194646036, |
| "max": 0.01662841827559079, |
| "count": 17 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20618115810793824, |
| "min": 0.029831896778584145, |
| "max": 0.23279785585827106, |
| "count": 17 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.736990278178568e-06, |
| "min": 7.736990278178568e-06, |
| "max": 0.00014840397553202503, |
| "count": 17 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010831786389449995, |
| "min": 0.00010831786389449995, |
| "max": 0.0019965490344839004, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1025789642857143, |
| "min": 0.1025789642857143, |
| "max": 0.14946797500000003, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4361055, |
| "min": 0.5978719000000001, |
| "max": 2.1228397, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002676385321428571, |
| "min": 0.0002676385321428571, |
| "max": 0.0049518507025, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00374693945, |
| "min": 0.00374693945, |
| "max": 0.06662505838999999, |
| "count": 17 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012849266640841961, |
| "min": 0.012849266640841961, |
| "max": 0.025123387575149536, |
| "count": 17 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1798897385597229, |
| "min": 0.10049355030059814, |
| "max": 0.34496626257896423, |
| "count": 17 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 17 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 17 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1733783832", |
| "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", |
| "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 --resume", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.5.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1733785683" |
| }, |
| "total": 1850.6261229560005, |
| "count": 1, |
| "self": 0.7861319750008988, |
| "children": { |
| "run_training.setup": { |
| "total": 0.2539880539998194, |
| "count": 1, |
| "self": 0.2539880539998194 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1849.5860029269998, |
| "count": 1, |
| "self": 1.294645876127106, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.979598797999643, |
| "count": 1, |
| "self": 4.979598797999643 |
| }, |
| "TrainerController.advance": { |
| "total": 1843.1734095468728, |
| "count": 32233, |
| "self": 1.3679021679754442, |
| "children": { |
| "env_step": { |
| "total": 1256.8318886708657, |
| "count": 32233, |
| "self": 1168.7748687008343, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 87.28985066505447, |
| "count": 32233, |
| "self": 3.8919610000293687, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 83.3978896650251, |
| "count": 31317, |
| "self": 83.3978896650251 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7671693049769601, |
| "count": 32233, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1845.6630181171486, |
| "count": 32233, |
| "is_parallel": true, |
| "self": 773.4202299681347, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005147855999894091, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.001947864999237936, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.003199991000656155, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.003199991000656155 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.16988620899974194, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008106089990178589, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005216389999986859, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005216389999986859 |
| }, |
| "communicator.exchange": { |
| "total": 0.16614378400026908, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.16614378400026908 |
| }, |
| "steps_from_proto": { |
| "total": 0.002410177000456315, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004954500009262119, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001914726999530103, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001914726999530103 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1072.242788149014, |
| "count": 32232, |
| "is_parallel": true, |
| "self": 25.801126414867213, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 15.795808573142494, |
| "count": 32232, |
| "is_parallel": true, |
| "self": 15.795808573142494 |
| }, |
| "communicator.exchange": { |
| "total": 962.7423670060152, |
| "count": 32232, |
| "is_parallel": true, |
| "self": 962.7423670060152 |
| }, |
| "steps_from_proto": { |
| "total": 67.90348615498897, |
| "count": 32232, |
| "is_parallel": true, |
| "self": 14.518019982688202, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 53.38546617230077, |
| "count": 257856, |
| "is_parallel": true, |
| "self": 53.38546617230077 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 584.9736187080316, |
| "count": 32233, |
| "self": 2.51433974900101, |
| "children": { |
| "process_trajectory": { |
| "total": 90.57405441503033, |
| "count": 32233, |
| "self": 90.2546898820301, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3193645330002255, |
| "count": 2, |
| "self": 0.3193645330002255 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 491.88522454400027, |
| "count": 235, |
| "self": 194.21853590600313, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 297.66668863799714, |
| "count": 11337, |
| "self": 297.66668863799714 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.4770002962904982e-06, |
| "count": 1, |
| "self": 1.4770002962904982e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.13834722899991903, |
| "count": 1, |
| "self": 0.005393270999775268, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13295395800014376, |
| "count": 1, |
| "self": 0.13295395800014376 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
