{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.014378581196069717, "min": 0.014378581196069717, "max": 1.1409854888916016, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 718.0088500976562, "min": 718.0088500976562, "max": 57104.04296875, "count": 100 }, "Pyramids.Step.mean": { "value": 4999927.0, "min": 49893.0, "max": 4999927.0, "count": 100 }, "Pyramids.Step.sum": { "value": 4999927.0, "min": 49893.0, "max": 4999927.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09485006332397461, "min": -0.1126532256603241, "max": -0.0404495894908905, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -37.940025329589844, "min": -45.286598205566406, "max": -16.26073455810547, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4209729731082916, "min": 0.36038607358932495, "max": 0.5095276236534119, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 168.38919067382812, "min": 144.8751983642578, "max": 203.301513671875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06919115815991603, "min": 0.06446659878637029, "max": 0.07176302614996401, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.5913966376780686, "min": 1.0376964549887793, "max": 1.7208278710410618, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00038847397338177977, "min": 9.671289162736008e-05, "max": 0.00699471286615124, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.008934901387780934, "min": 0.002321109399056642, "max": 0.10492069299226861, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5136621041747814e-06, "min": 1.5136621041747814e-06, "max": 0.00029833182855605736, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.4814228396019974e-05, "min": 3.4814228396019974e-05, "max": 0.006382229512590219, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050452086956524, "min": 0.10050452086956524, "max": 0.19944394266666665, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3116039800000006, "min": 2.3116039800000006, "max": 4.427409780000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.040163486956519e-05, "min": 6.040163486956519e-05, "max": 0.0099444498724, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0013892376019999993, "min": 0.0013892376019999993, "max": 0.21275823702200003, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.4166781008243561, "min": 0.35349857807159424, "max": 0.5433374047279358, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 9.583596229553223, "min": 7.0089263916015625, "max": 10.19491195678711, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 987.32, "min": 941.5357142857143, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 49366.0, "min": 47253.0, "max": 58457.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9478520506620407, "min": -0.9996980906409376, "max": -0.7592727769504893, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -47.392602533102036, "min": -53.49760294705629, "max": -40.08940251916647, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9478520506620407, "min": -0.9996980906409376, "max": -0.7592727769504893, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -47.392602533102036, "min": -53.49760294705629, "max": -40.08940251916647, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 4.110766069889069, "min": 3.515966962514953, "max": 7.437996529353161, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 205.53830349445343, "min": 178.05099934339523, "max": 357.02383340895176, "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": "1663840478", "python_version": "3.7.14 (default, Sep 8 2022, 00:06:44) \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-5M --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": "1663849344" }, "total": 8866.411017946, "count": 1, "self": 0.44408365200069966, "children": { "run_training.setup": { "total": 0.04288288999987344, "count": 1, "self": 0.04288288999987344 }, "TrainerController.start_learning": { "total": 8865.924051404, "count": 1, "self": 6.678796679703737, "children": { "TrainerController._reset_env": { "total": 6.4606735729998945, "count": 1, "self": 6.4606735729998945 }, "TrainerController.advance": { "total": 8852.683410777294, "count": 316178, "self": 7.329978573205153, "children": { "env_step": { "total": 5348.49654544502, "count": 316178, "self": 4805.117614749303, "children": { "SubprocessEnvManager._take_step": { "total": 539.6834890948003, "count": 316178, "self": 23.72044759193841, "children": { "TorchPolicy.evaluate": { "total": 515.9630415028619, "count": 312553, "self": 177.01931311966973, "children": { "TorchPolicy.sample_actions": { "total": 338.94372838319214, "count": 312553, "self": 338.94372838319214 } } } } }, "workers": { "total": 3.695441600916638, "count": 316178, "self": 0.0, "children": { "worker_root": { "total": 8844.593194344372, "count": 316178, "is_parallel": true, "self": 4562.152589237141, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019833100000141712, "count": 1, "is_parallel": true, "self": 0.000731114000245725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012521959997684462, "count": 8, "is_parallel": true, "self": 0.0012521959997684462 } } }, "UnityEnvironment.step": { "total": 0.04935210899975573, "count": 1, "is_parallel": true, "self": 0.0005626980000670301, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047847299993009074, "count": 1, "is_parallel": true, "self": 0.00047847299993009074 }, "communicator.exchange": { "total": 0.04577883000001748, "count": 1, "is_parallel": true, "self": 0.04577883000001748 }, "steps_from_proto": { "total": 0.002532107999741129, "count": 1, "is_parallel": true, "self": 0.0006620560002374987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018700519995036302, "count": 8, "is_parallel": true, "self": 0.0018700519995036302 } } } } } } }, "UnityEnvironment.step": { "total": 4282.440605107231, "count": 316177, "is_parallel": true, "self": 143.50681162730507, "children": { "UnityEnvironment._generate_step_input": { "total": 122.22965864353364, "count": 316177, "is_parallel": true, "self": 122.22965864353364 }, "communicator.exchange": { "total": 3531.90158591198, "count": 316177, "is_parallel": true, "self": 3531.90158591198 }, "steps_from_proto": { "total": 484.80254892441235, "count": 316177, "is_parallel": true, "self": 120.18634695644596, "children": { "_process_rank_one_or_two_observation": { "total": 364.6162019679664, "count": 2529416, "is_parallel": true, "self": 364.6162019679664 } } } } } } } } } } }, "trainer_advance": { "total": 3496.856886759068, "count": 316178, "self": 12.676182660392442, "children": { "process_trajectory": { "total": 821.0636206006761, "count": 316178, "self": 820.0258232286751, "children": { "RLTrainer._checkpoint": { "total": 1.0377973720010232, "count": 10, "self": 1.0377973720010232 } } }, "_update_policy": { "total": 2663.1170834979994, "count": 2309, "self": 1039.2916768168093, "children": { "TorchPPOOptimizer.update": { "total": 1623.82540668119, "count": 113844, "self": 1623.82540668119 } } } } } } }, "trainer_threads": { "total": 1.1210013326490298e-06, "count": 1, "self": 1.1210013326490298e-06 }, "TrainerController._save_models": { "total": 0.10116925300098956, "count": 1, "self": 0.0016039920010371134, "children": { "RLTrainer._checkpoint": { "total": 0.09956526099995244, "count": 1, "self": 0.09956526099995244 } } } } } } }