| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.46562087535858154, |
| "min": 0.46562087535858154, |
| "max": 1.3739114999771118, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 13946.2763671875, |
| "min": 13946.2763671875, |
| "max": 41678.98046875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989922.0, |
| "min": 29924.0, |
| "max": 989922.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989922.0, |
| "min": 29924.0, |
| "max": 989922.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4119535982608795, |
| "min": -0.11586210131645203, |
| "max": 0.49002864956855774, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 110.81552124023438, |
| "min": -28.154491424560547, |
| "max": 132.3077392578125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.1409996896982193, |
| "min": -0.0008035409264266491, |
| "max": 0.41958507895469666, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 37.928916931152344, |
| "min": -0.21454542875289917, |
| "max": 99.44166564941406, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06783897690045358, |
| "min": 0.06582488973572985, |
| "max": 0.07891760675065687, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9497456766063502, |
| "min": 0.5524232472545981, |
| "max": 1.0475720871398544, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01805466054342798, |
| "min": 0.0004771958673514287, |
| "max": 0.019556853611512843, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.25276524760799174, |
| "min": 0.006203546275568573, |
| "max": 0.2737959505611798, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.56914033412857e-06, |
| "min": 7.56914033412857e-06, |
| "max": 0.00029523411587434285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010596796467779999, |
| "min": 0.00010596796467779999, |
| "max": 0.003491480536173199, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10252301428571428, |
| "min": 0.10252301428571428, |
| "max": 0.1984113714285714, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4353221999999999, |
| "min": 1.3888795999999999, |
| "max": 2.5265952, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002620491271428572, |
| "min": 0.0002620491271428572, |
| "max": 0.009841296005714286, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003668687780000001, |
| "min": 0.003668687780000001, |
| "max": 0.11639629732000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012440630234777927, |
| "min": 0.012440630234777927, |
| "max": 0.5543642640113831, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17416882514953613, |
| "min": 0.17416882514953613, |
| "max": 3.880549669265747, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 404.24, |
| "min": 368.54545454545456, |
| "max": 996.5, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30318.0, |
| "min": 16723.0, |
| "max": 33253.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.409007972975572, |
| "min": -0.9348313014488667, |
| "max": 1.5306078668095564, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 105.6755979731679, |
| "min": -29.914601646363735, |
| "max": 118.40859808027744, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.409007972975572, |
| "min": -0.9348313014488667, |
| "max": 1.5306078668095564, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 105.6755979731679, |
| "min": -29.914601646363735, |
| "max": 118.40859808027744, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.051315635362795244, |
| "min": 0.051315635362795244, |
| "max": 11.351491233881783, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.8486726522096433, |
| "min": 3.8486726522096433, |
| "max": 192.9753509759903, |
| "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": "1685921470", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 Training3 --no-graphics", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1685924221" |
| }, |
| "total": 2750.914778442, |
| "count": 1, |
| "self": 1.111541041998862, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0433936490007909, |
| "count": 1, |
| "self": 0.0433936490007909 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2749.7598437510005, |
| "count": 1, |
| "self": 2.1142418758245185, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.011762643000111, |
| "count": 1, |
| "self": 4.011762643000111 |
| }, |
| "TrainerController.advance": { |
| "total": 2743.4562539961735, |
| "count": 63598, |
| "self": 2.054923410923948, |
| "children": { |
| "env_step": { |
| "total": 1988.0888174311585, |
| "count": 63598, |
| "self": 1828.8161527150696, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 158.0274389138758, |
| "count": 63598, |
| "self": 6.863652546757294, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 151.16378636711852, |
| "count": 62544, |
| "self": 151.16378636711852 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.245225802213099, |
| "count": 63598, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2742.234224333288, |
| "count": 63598, |
| "is_parallel": true, |
| "self": 1078.8577447883508, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0022228649995668093, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007093330023053568, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015135319972614525, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015135319972614525 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05813020899950061, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006391969982360024, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000631525001153932, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000631525001153932 |
| }, |
| "communicator.exchange": { |
| "total": 0.05477555300058157, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05477555300058157 |
| }, |
| "steps_from_proto": { |
| "total": 0.0020839339995291084, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00041786199835769366, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016660720011714147, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016660720011714147 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1663.376479544937, |
| "count": 63597, |
| "is_parallel": true, |
| "self": 42.9770534839372, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 30.315071898996393, |
| "count": 63597, |
| "is_parallel": true, |
| "self": 30.315071898996393 |
| }, |
| "communicator.exchange": { |
| "total": 1456.6970558618304, |
| "count": 63597, |
| "is_parallel": true, |
| "self": 1456.6970558618304 |
| }, |
| "steps_from_proto": { |
| "total": 133.38729830017292, |
| "count": 63597, |
| "is_parallel": true, |
| "self": 28.4494313408959, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 104.93786695927702, |
| "count": 508776, |
| "is_parallel": true, |
| "self": 104.93786695927702 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 753.312513154091, |
| "count": 63598, |
| "self": 4.106107266241452, |
| "children": { |
| "process_trajectory": { |
| "total": 136.51537153384015, |
| "count": 63598, |
| "self": 136.18674688383908, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.32862465000107477, |
| "count": 2, |
| "self": 0.32862465000107477 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 612.6910343540094, |
| "count": 454, |
| "self": 391.0272584921131, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 221.66377586189628, |
| "count": 22818, |
| "self": 221.66377586189628 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.489001078880392e-06, |
| "count": 1, |
| "self": 1.489001078880392e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.17758374700133572, |
| "count": 1, |
| "self": 0.002272608002385823, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1753111389989499, |
| "count": 1, |
| "self": 0.1753111389989499 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
