{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14502044022083282, "min": 0.12752866744995117, "max": 1.4461236000061035, "count": 166 }, "Pyramids.Policy.Entropy.sum": { "value": 4390.05859375, "min": 3852.385986328125, "max": 43869.60546875, "count": 166 }, "Pyramids.Step.mean": { "value": 4979996.0, "min": 29952.0, "max": 4979996.0, "count": 166 }, "Pyramids.Step.sum": { "value": 4979996.0, "min": 29952.0, "max": 4979996.0, "count": 166 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.839003324508667, "min": -0.21277064085006714, "max": 0.9030649662017822, "count": 166 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 251.70098876953125, "min": -50.42664337158203, "max": 283.5624084472656, "count": 166 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005599901080131531, "min": -0.3180496096611023, "max": 1.1370110511779785, "count": 166 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6799702644348145, "min": -85.55534362792969, "max": 274.0196533203125, "count": 166 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.031900718597517835, "min": 0.024253821147361857, "max": 0.0378008363732821, "count": 166 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4466100603652497, "min": 0.2646058546129747, "max": 0.5254435648287957, "count": 166 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014076724435047561, "min": 0.001039826701958385, "max": 0.06370900165001374, "count": 166 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19707414209066584, "min": 0.011562729627864124, "max": 0.8919260231001924, "count": 166 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0990493003500023e-06, "min": 2.0990493003500023e-06, "max": 0.0002990301260375771, "count": 166 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.9386690204900035e-05, "min": 2.9386690204900035e-05, "max": 0.0039736534754489, "count": 166 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10069965, "min": 0.10069965, "max": 0.19967670857142858, "count": 166 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4097951, "min": 1.39773696, "max": 2.8245511, "count": 166 }, "Pyramids.Policy.Beta.mean": { "value": 7.989503500000008e-05, "min": 7.989503500000008e-05, "max": 0.009967703186285714, "count": 166 }, "Pyramids.Policy.Beta.sum": { "value": 0.0011185304900000013, "min": 0.0011185304900000013, "max": 0.13247265488999999, "count": 166 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008710531517863274, "min": 0.008710531517863274, "max": 1.3006354570388794, "count": 166 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12194743752479553, "min": 0.12194743752479553, "max": 9.104448318481445, "count": 166 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 217.4485294117647, "min": 191.51700680272108, "max": 999.0, "count": 166 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29573.0, "min": 15984.0, "max": 33077.0, "count": 166 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7664262636082015, "min": -1.0000000521540642, "max": 1.8087852218207097, "count": 166 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 242.00039811432362, "min": -31.998401656746864, "max": 272.9329990595579, "count": 166 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7664262636082015, "min": -1.0000000521540642, "max": 1.8087852218207097, "count": 166 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 242.00039811432362, "min": -31.998401656746864, "max": 272.9329990595579, "count": 166 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019236186884948433, "min": 0.01854462163040201, "max": 14.69947513192892, "count": 166 }, "Pyramids.Policy.RndReward.sum": { "value": 2.635357603237935, "min": 2.635357603237935, "max": 409.5954595208168, "count": 166 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 166 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 166 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1659375787", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1.21.6", "end_time_seconds": "1659386195" }, "total": 10407.217677057999, "count": 1, "self": 0.5280591439986893, "children": { "run_training.setup": { "total": 0.042697342999986176, "count": 1, "self": 0.042697342999986176 }, "TrainerController.start_learning": { "total": 10406.646920571, "count": 1, "self": 7.817220536928289, "children": { "TrainerController._reset_env": { "total": 9.272099446000084, "count": 1, "self": 9.272099446000084 }, "TrainerController.advance": { "total": 10389.461723815073, "count": 326524, "self": 7.88366087736722, "children": { "env_step": { "total": 7664.625016691063, "count": 326524, "self": 7140.773809630927, "children": { "SubprocessEnvManager._take_step": { "total": 519.8157740460196, "count": 326524, "self": 23.09924651539302, "children": { "TorchPolicy.evaluate": { "total": 496.71652753062654, "count": 312567, "self": 174.31968312556387, "children": { "TorchPolicy.sample_actions": { "total": 322.39684440506267, "count": 312567, "self": 322.39684440506267 } } } } }, "workers": { "total": 4.03543301411662, "count": 326524, "self": 0.0, "children": { "worker_root": { "total": 10386.436381120398, "count": 326524, "is_parallel": true, "self": 3768.504369527115, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007553469000072255, "count": 1, "is_parallel": true, "self": 0.003791787000295699, "children": { "_process_rank_one_or_two_observation": { "total": 0.003761681999776556, "count": 8, "is_parallel": true, "self": 0.003761681999776556 } } }, "UnityEnvironment.step": { "total": 0.04410118600003443, "count": 1, "is_parallel": true, "self": 0.0005384729998922921, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004733550000537434, "count": 1, "is_parallel": true, "self": 0.0004733550000537434 }, "communicator.exchange": { "total": 0.041371582000010676, "count": 1, "is_parallel": true, "self": 0.041371582000010676 }, "steps_from_proto": { "total": 0.0017177760000777198, "count": 1, "is_parallel": true, "self": 0.00044001500009471783, "children": { "_process_rank_one_or_two_observation": { "total": 0.001277760999983002, "count": 8, "is_parallel": true, "self": 0.001277760999983002 } } } } } } }, "UnityEnvironment.step": { "total": 6617.932011593283, "count": 326523, "is_parallel": true, "self": 140.71539358129394, "children": { "UnityEnvironment._generate_step_input": { "total": 115.27701619413165, "count": 326523, "is_parallel": true, "self": 115.27701619413165 }, "communicator.exchange": { "total": 5896.185486113087, "count": 326523, "is_parallel": true, "self": 5896.185486113087 }, "steps_from_proto": { "total": 465.75411570477047, "count": 326523, "is_parallel": true, "self": 117.12614435011949, "children": { "_process_rank_one_or_two_observation": { "total": 348.627971354651, "count": 2612184, "is_parallel": true, "self": 348.627971354651 } } } } } } } } } } }, "trainer_advance": { "total": 2716.9530462466423, "count": 326524, "self": 14.606089183349013, "children": { "process_trajectory": { "total": 811.7579510102942, "count": 326524, "self": 810.749741571294, "children": { "RLTrainer._checkpoint": { "total": 1.0082094390002112, "count": 10, "self": 1.0082094390002112 } } }, "_update_policy": { "total": 1890.5890060529991, "count": 2334, "self": 1037.4484621020451, "children": { "TorchPPOOptimizer.update": { "total": 853.1405439509539, "count": 28356, "self": 853.1405439509539 } } } } } } }, "trainer_threads": { "total": 1.207999957841821e-06, "count": 1, "self": 1.207999957841821e-06 }, "TrainerController._save_models": { "total": 0.09587556499900529, "count": 1, "self": 0.0018247179978061467, "children": { "RLTrainer._checkpoint": { "total": 0.09405084700119914, "count": 1, "self": 0.09405084700119914 } } } } } } }