{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13450214266777039, "min": 0.13450214266777039, "max": 1.4417102336883545, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4039.3681640625, "min": 4039.3681640625, "max": 43735.72265625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999880.0, "min": 29952.0, "max": 2999880.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999880.0, "min": 29952.0, "max": 2999880.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7861818075180054, "min": -0.08832869678735733, "max": 0.9109013080596924, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 231.137451171875, "min": -21.4638729095459, "max": 282.8077392578125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007935836911201477, "min": -0.060711074620485306, "max": 0.2938811779022217, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3331360816955566, "min": -17.12052345275879, "max": 70.82536315917969, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06922509427697929, "min": 0.06282065961568152, "max": 0.07382104506148841, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9691513198777101, "min": 0.5158082503439383, "max": 1.0941049003352723, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015434782882082455, "min": 0.0007816446250068856, "max": 0.017807680356455836, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21608696034915437, "min": 0.010161380125089513, "max": 0.2510339766546773, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5088137828095251e-06, "min": 1.5088137828095251e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.112339295933335e-05, "min": 2.112339295933335e-05, "max": 0.004011469362843566, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050290476190478, "min": 0.10050290476190478, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070406666666668, "min": 1.3962282666666668, "max": 2.7974441666666663, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.024018571428576e-05, "min": 6.024018571428576e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008433626000000006, "min": 0.0008433626000000006, "max": 0.13372192769, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005911039654165506, "min": 0.005911039654165506, "max": 0.49577733874320984, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08275455236434937, "min": 0.08275455236434937, "max": 3.4704413414001465, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.33070866141733, "min": 183.09815950920245, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29125.0, "min": 15984.0, "max": 32838.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7076551006652239, "min": -1.0000000521540642, "max": 1.8169018266025496, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 216.87219778448343, "min": -29.313801646232605, "max": 296.1549977362156, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7076551006652239, "min": -1.0000000521540642, "max": 1.8169018266025496, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 216.87219778448343, "min": -29.313801646232605, "max": 296.1549977362156, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014183733668329567, "min": 0.012905429825872367, "max": 9.60736127011478, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8013341758778552, "min": 1.8013341758778552, "max": 153.71778032183647, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674335711", "python_version": "3.8.15 (default, Nov 24 2022, 15:19:38) \n[GCC 11.2.0]", "command_line_arguments": "/home/boris.ustyugov/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-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": "1.8.2", "numpy_version": "1.23.4", "end_time_seconds": "1674341960" }, "total": 6249.385782581288, "count": 1, "self": 0.3712270692922175, "children": { "run_training.setup": { "total": 0.01450786693021655, "count": 1, "self": 0.01450786693021655 }, "TrainerController.start_learning": { "total": 6249.000047645066, "count": 1, "self": 2.434942554216832, "children": { "TrainerController._reset_env": { "total": 2.555532200727612, "count": 1, "self": 2.555532200727612 }, "TrainerController.advance": { "total": 6243.948823351413, "count": 196111, "self": 2.5357573362998664, "children": { "env_step": { "total": 4422.413879491389, "count": 196111, "self": 4207.721656929236, "children": { "SubprocessEnvManager._take_step": { "total": 213.22899888874963, "count": 196111, "self": 8.229264385998249, "children": { "TorchPolicy.evaluate": { "total": 204.99973450275138, "count": 187559, "self": 66.67140922276303, "children": { "TorchPolicy.sample_actions": { "total": 138.32832527998835, "count": 187559, "self": 138.32832527998835 } } } } }, "workers": { "total": 1.463223673403263, "count": 196111, "self": 0.0, "children": { "worker_root": { "total": 6239.279044141527, "count": 196111, "is_parallel": true, "self": 2315.2968790563755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00148296682164073, "count": 1, "is_parallel": true, "self": 0.0004582256078720093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010247412137687206, "count": 8, "is_parallel": true, "self": 0.0010247412137687206 } } }, "UnityEnvironment.step": { "total": 0.043039778247475624, "count": 1, "is_parallel": true, "self": 0.00030612340196967125, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006346949376165867, "count": 1, "is_parallel": true, "self": 0.0006346949376165867 }, "communicator.exchange": { "total": 0.04127544490620494, "count": 1, "is_parallel": true, "self": 0.04127544490620494 }, "steps_from_proto": { "total": 0.0008235150016844273, "count": 1, "is_parallel": true, "self": 0.00023071793839335442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005927970632910728, "count": 8, "is_parallel": true, "self": 0.0005927970632910728 } } } } } } }, "UnityEnvironment.step": { "total": 3923.982165085152, "count": 196110, "is_parallel": true, "self": 129.89307804917917, "children": { "UnityEnvironment._generate_step_input": { "total": 87.97066220268607, "count": 196110, "is_parallel": true, "self": 87.97066220268607 }, "communicator.exchange": { "total": 3347.4763779682107, "count": 196110, "is_parallel": true, "self": 3347.4763779682107 }, "steps_from_proto": { "total": 358.6420468650758, "count": 196110, "is_parallel": true, "self": 84.73668967047706, "children": { "_process_rank_one_or_two_observation": { "total": 273.90535719459876, "count": 1568880, "is_parallel": true, "self": 273.90535719459876 } } } } } } } } } } }, "trainer_advance": { "total": 1818.9991865237243, "count": 196111, "self": 4.275737033225596, "children": { "process_trajectory": { "total": 292.23973047500476, "count": 196111, "self": 291.8720959927887, "children": { "RLTrainer._checkpoint": { "total": 0.36763448221608996, "count": 6, "self": 0.36763448221608996 } } }, "_update_policy": { "total": 1522.483719015494, "count": 1400, "self": 311.9060413381085, "children": { "TorchPPOOptimizer.update": { "total": 1210.5776776773855, "count": 68361, "self": 1210.5776776773855 } } } } } } }, "trainer_threads": { "total": 7.539056241512299e-07, "count": 1, "self": 7.539056241512299e-07 }, "TrainerController._save_models": { "total": 0.06074878480285406, "count": 1, "self": 0.0008047227747738361, "children": { "RLTrainer._checkpoint": { "total": 0.059944062028080225, "count": 1, "self": 0.059944062028080225 } } } } } } }