{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.514694333076477, "min": 1.514694333076477, "max": 1.514694333076477, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 45949.765625, "min": 45949.765625, "max": 45949.765625, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1696854531764984, "min": 0.1696854531764984, "max": 0.1696854531764984, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 40.2154541015625, "min": 40.2154541015625, "max": 40.2154541015625, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.21470907330513, "min": 0.21470907330513, "max": 0.21470907330513, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 50.886051177978516, "min": 50.886051177978516, "max": 50.886051177978516, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06906276903268523, "min": 0.06906276903268523, "max": 0.06906276903268523, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.48343938322879654, "min": 0.48343938322879654, "max": 0.48343938322879654, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0030825327752555393, "min": 0.0030825327752555393, "max": 0.0030825327752555393, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.021577729426788775, "min": 0.021577729426788775, "max": 0.021577729426788775, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00029838354339596195, "min": 0.00029838354339596195, "max": 0.00029838354339596195, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020886848037717336, "min": 0.0020886848037717336, "max": 0.0020886848037717336, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19946118095238097, "min": 0.19946118095238097, "max": 0.19946118095238097, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3962282666666668, "min": 1.3962282666666668, "max": 1.3962282666666668, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.009946171977142856, "min": 0.009946171977142856, "max": 0.009946171977142856, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.06962320384, "min": 0.06962320384, "max": 0.06962320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.27302494645118713, "min": 0.27302494645118713, "max": 0.27302494645118713, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.9111745357513428, "min": 1.9111745357513428, "max": 1.9111745357513428, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 5.582357250154018, "min": 5.582357250154018, "max": 5.582357250154018, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 89.3177160024643, "min": 89.3177160024643, "max": 89.3177160024643, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670719846", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \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": "1670719911" }, "total": 65.32562540000026, "count": 1, "self": 0.2732738910003718, "children": { "run_training.setup": { "total": 0.10450554999988526, "count": 1, "self": 0.10450554999988526 }, "TrainerController.start_learning": { "total": 64.947845959, "count": 1, "self": 0.036833548993399745, "children": { "TrainerController._reset_env": { "total": 9.691834345999723, "count": 1, "self": 9.691834345999723 }, "TrainerController.advance": { "total": 55.05798179200701, "count": 2087, "self": 0.04285855100852132, "children": { "env_step": { "total": 34.158301148999726, "count": 2087, "self": 30.593413590979708, "children": { "SubprocessEnvManager._take_step": { "total": 3.5420265240104527, "count": 2087, "self": 0.13895252601059838, "children": { "TorchPolicy.evaluate": { "total": 3.4030739979998543, "count": 2087, "self": 1.1006341570018776, "children": { "TorchPolicy.sample_actions": { "total": 2.3024398409979767, "count": 2087, "self": 2.3024398409979767 } } } } }, "workers": { "total": 0.02286103400956563, "count": 2086, "self": 0.0, "children": { "worker_root": { "total": 64.79358462200298, "count": 2086, "is_parallel": true, "self": 37.29874719399777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005319279000104871, "count": 1, "is_parallel": true, "self": 0.0032839370005603996, "children": { "_process_rank_one_or_two_observation": { "total": 0.002035341999544471, "count": 8, "is_parallel": true, "self": 0.002035341999544471 } } }, "UnityEnvironment.step": { "total": 0.05611556299982112, "count": 1, "is_parallel": true, "self": 0.0004937759999847913, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043956699983027647, "count": 1, "is_parallel": true, "self": 0.00043956699983027647 }, "communicator.exchange": { "total": 0.05338901499999338, "count": 1, "is_parallel": true, "self": 0.05338901499999338 }, "steps_from_proto": { "total": 0.0017932050000126765, "count": 1, "is_parallel": true, "self": 0.00041667699997560703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013765280000370694, "count": 8, "is_parallel": true, "self": 0.0013765280000370694 } } } } } } }, "UnityEnvironment.step": { "total": 27.494837428005212, "count": 2085, "is_parallel": true, "self": 0.8860800980214663, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7072013289916868, "count": 2085, "is_parallel": true, "self": 0.7072013289916868 }, "communicator.exchange": { "total": 22.961812080985965, "count": 2085, "is_parallel": true, "self": 22.961812080985965 }, "steps_from_proto": { "total": 2.9397439200060944, "count": 2085, "is_parallel": true, "self": 0.6741382809900642, "children": { "_process_rank_one_or_two_observation": { "total": 2.26560563901603, "count": 16680, "is_parallel": true, "self": 2.26560563901603 } } } } } } } } } } }, "trainer_advance": { "total": 20.856822091998765, "count": 2086, "self": 0.043949550004981575, "children": { "process_trajectory": { "total": 4.718156342994007, "count": 2086, "self": 4.718156342994007 }, "_update_policy": { "total": 16.094716198999777, "count": 8, "self": 6.1049739409913855, "children": { "TorchPPOOptimizer.update": { "total": 9.989742258008391, "count": 750, "self": 9.989742258008391 } } } } } } }, "trainer_threads": { "total": 1.1729998732334934e-06, "count": 1, "self": 1.1729998732334934e-06 }, "TrainerController._save_models": { "total": 0.16119509899999684, "count": 1, "self": 0.0018349309998484387, "children": { "RLTrainer._checkpoint": { "total": 0.1593601680001484, "count": 1, "self": 0.1593601680001484 } } } } } } }