{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5399750471115112, "min": 0.5399750471115112, "max": 1.4519519805908203, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16251.0888671875, "min": 16251.0888671875, "max": 44046.4140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29872.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29872.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3227290213108063, "min": -0.09820189327001572, "max": 0.3537415564060211, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.9095458984375, "min": -23.666656494140625, "max": 92.68029022216797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4602455794811249, "min": -0.03164992853999138, "max": 0.4602455794811249, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 119.66384887695312, "min": -8.260631561279297, "max": 119.66384887695312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06884274974748092, "min": 0.06425404305401673, "max": 0.07244754452821675, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9637984964647329, "min": 0.5768311019954242, "max": 1.042963239150898, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0557487743714037, "min": 0.0005109460279241244, "max": 0.0557487743714037, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7804828411996518, "min": 0.006642298363013617, "max": 0.7804828411996518, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.319261845992866e-06, "min": 7.319261845992866e-06, "max": 0.0002947644017452, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010246966584390011, "min": 0.00010246966584390011, "max": 0.0033729199756934, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243972142857141, "min": 0.10243972142857141, "max": 0.1982548, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341560999999998, "min": 1.4341560999999998, "max": 2.4851554, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025372817071428596, "min": 0.00025372817071428596, "max": 0.009825654520000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035521943900000035, "min": 0.0035521943900000035, "max": 0.11244822934000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010192131623625755, "min": 0.010192131623625755, "max": 0.6322476863861084, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14268983900547028, "min": 0.14268983900547028, "max": 5.057981491088867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 502.3898305084746, "min": 466.55555555555554, "max": 995.5806451612904, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29641.0, "min": 17182.0, "max": 32121.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2263321791917592, "min": -0.925387146251817, "max": 1.3783718453487381, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.35359857231379, "min": -28.687001533806324, "max": 88.21579810231924, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2263321791917592, "min": -0.925387146251817, "max": 1.3783718453487381, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.35359857231379, "min": -28.687001533806324, "max": 88.21579810231924, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0536589139443033, "min": 0.0536589139443033, "max": 13.030622682637638, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1658759227138944, "min": 3.1658759227138944, "max": 234.5512082874775, "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": "1691567840", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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", "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": "1691569980" }, "total": 2139.2600702560003, "count": 1, "self": 0.47706513700040887, "children": { "run_training.setup": { "total": 0.039285389999804465, "count": 1, "self": 0.039285389999804465 }, "TrainerController.start_learning": { "total": 2138.743719729, "count": 1, "self": 1.3533703351095028, "children": { "TrainerController._reset_env": { "total": 4.853995445000237, "count": 1, "self": 4.853995445000237 }, "TrainerController.advance": { "total": 2132.443922358891, "count": 63487, "self": 1.3950255468880641, "children": { "env_step": { "total": 1463.652125551053, "count": 63487, "self": 1353.3037801051, "children": { "SubprocessEnvManager._take_step": { "total": 109.53678360307913, "count": 63487, "self": 4.650957185085645, "children": { "TorchPolicy.evaluate": { "total": 104.88582641799348, "count": 62570, "self": 104.88582641799348 } } }, "workers": { "total": 0.8115618428737434, "count": 63487, "self": 0.0, "children": { "worker_root": { "total": 2133.9334333939846, "count": 63487, "is_parallel": true, "self": 894.3006750360692, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017576329996700224, "count": 1, "is_parallel": true, "self": 0.0005511569988811971, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012064760007888253, "count": 8, "is_parallel": true, "self": 0.0012064760007888253 } } }, "UnityEnvironment.step": { "total": 0.08123048800007382, "count": 1, "is_parallel": true, "self": 0.0006107010003688629, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048702499998398707, "count": 1, "is_parallel": true, "self": 0.00048702499998398707 }, "communicator.exchange": { "total": 0.07832975299970713, "count": 1, "is_parallel": true, "self": 0.07832975299970713 }, "steps_from_proto": { "total": 0.0018030090000138443, "count": 1, "is_parallel": true, "self": 0.00035532799984139274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014476810001724516, "count": 8, "is_parallel": true, "self": 0.0014476810001724516 } } } } } } }, "UnityEnvironment.step": { "total": 1239.6327583579155, "count": 63486, "is_parallel": true, "self": 34.29625882991786, "children": { "UnityEnvironment._generate_step_input": { "total": 23.2207602299859, "count": 63486, "is_parallel": true, "self": 23.2207602299859 }, "communicator.exchange": { "total": 1077.6690098899317, "count": 63486, "is_parallel": true, "self": 1077.6690098899317 }, "steps_from_proto": { "total": 104.44672940808005, "count": 63486, "is_parallel": true, "self": 20.131587631167804, "children": { "_process_rank_one_or_two_observation": { "total": 84.31514177691224, "count": 507888, "is_parallel": true, "self": 84.31514177691224 } } } } } } } } } } }, "trainer_advance": { "total": 667.3967712609501, "count": 63487, "self": 2.476039558957382, "children": { "process_trajectory": { "total": 110.98110709299681, "count": 63487, "self": 110.77432993299726, "children": { "RLTrainer._checkpoint": { "total": 0.2067771599995467, "count": 2, "self": 0.2067771599995467 } } }, "_update_policy": { "total": 553.9396246089959, "count": 454, "self": 361.3766866469764, "children": { "TorchPPOOptimizer.update": { "total": 192.56293796201953, "count": 22785, "self": 192.56293796201953 } } } } } } }, "trainer_threads": { "total": 8.259994501713663e-07, "count": 1, "self": 8.259994501713663e-07 }, "TrainerController._save_models": { "total": 0.09243076399980055, "count": 1, "self": 0.0013125659997967887, "children": { "RLTrainer._checkpoint": { "total": 0.09111819800000376, "count": 1, "self": 0.09111819800000376 } } } } } } }