{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5659940242767334, "min": 0.5659940242767334, "max": 1.4491000175476074, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17296.77734375, "min": 17296.77734375, "max": 43959.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29962.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29962.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3790387213230133, "min": -0.15619845688343048, "max": 0.4330744445323944, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.20333862304688, "min": -37.17523193359375, "max": 116.49702453613281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.031373705714941025, "min": -0.0435170941054821, "max": 0.35047757625579834, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.376779556274414, "min": -11.706098556518555, "max": 83.41366577148438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06910815106571785, "min": 0.06353025187997784, "max": 0.07432123324275972, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.96751411492005, "min": 0.4949648961413621, "max": 1.0385407263392528, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013734349079771035, "min": 0.0005077537149246728, "max": 0.013734349079771035, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1922808871167945, "min": 0.00710855200894542, "max": 0.1922808871167945, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.68170458232143e-06, "min": 7.68170458232143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010754386415250002, "min": 0.00010754386415250002, "max": 0.0033820589726470994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256053571428571, "min": 0.10256053571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358475, "min": 1.3886848, "max": 2.5273529, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000265797517857143, "min": 0.000265797517857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037211652500000014, "min": 0.0037211652500000014, "max": 0.11276255470999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010631784796714783, "min": 0.010434563271701336, "max": 0.43777087330818176, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14884498715400696, "min": 0.14608389139175415, "max": 3.0643961429595947, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 420.4776119402985, "min": 420.4776119402985, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28172.0, "min": 16761.0, "max": 32944.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3453323352424538, "min": -0.9999806972280625, "max": 1.3765910126602472, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.48259879648685, "min": -30.99940161406994, "max": 92.23159784823656, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3453323352424538, "min": -0.9999806972280625, "max": 1.3765910126602472, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.48259879648685, "min": -30.99940161406994, "max": 92.23159784823656, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.046539756966761645, "min": 0.046539756966761645, "max": 9.354461896945448, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1647034737397917, "min": 3.1647034737397917, "max": 159.02585224807262, "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": "1691205679", "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": "1691208785" }, "total": 3106.0799635129997, "count": 1, "self": 0.5880169709994334, "children": { "run_training.setup": { "total": 0.05324194800004989, "count": 1, "self": 0.05324194800004989 }, "TrainerController.start_learning": { "total": 3105.4387045940002, "count": 1, "self": 2.319064513106241, "children": { "TrainerController._reset_env": { "total": 1.4463669840001785, "count": 1, "self": 1.4463669840001785 }, "TrainerController.advance": { "total": 3101.5582644668934, "count": 63461, "self": 2.4161078248753256, "children": { "env_step": { "total": 1970.0918238030567, "count": 63461, "self": 1829.2737128658973, "children": { "SubprocessEnvManager._take_step": { "total": 139.38906596808738, "count": 63461, "self": 6.903427539042241, "children": { "TorchPolicy.evaluate": { "total": 132.48563842904514, "count": 62564, "self": 132.48563842904514 } } }, "workers": { "total": 1.429044969072038, "count": 63461, "self": 0.0, "children": { "worker_root": { "total": 3098.9249258189107, "count": 63461, "is_parallel": true, "self": 1435.1968476059606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028094609997424413, "count": 1, "is_parallel": true, "self": 0.0009208379992742266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018886230004682147, "count": 8, "is_parallel": true, "self": 0.0018886230004682147 } } }, "UnityEnvironment.step": { "total": 0.08410254899990832, "count": 1, "is_parallel": true, "self": 0.0006836580000708636, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035321199993632035, "count": 1, "is_parallel": true, "self": 0.00035321199993632035 }, "communicator.exchange": { "total": 0.08075839899993298, "count": 1, "is_parallel": true, "self": 0.08075839899993298 }, "steps_from_proto": { "total": 0.0023072799999681592, "count": 1, "is_parallel": true, "self": 0.00048588799973003916, "children": { "_process_rank_one_or_two_observation": { "total": 0.00182139200023812, "count": 8, "is_parallel": true, "self": 0.00182139200023812 } } } } } } }, "UnityEnvironment.step": { "total": 1663.72807821295, "count": 63460, "is_parallel": true, "self": 46.39213143291181, "children": { "UnityEnvironment._generate_step_input": { "total": 25.999447167046128, "count": 63460, "is_parallel": true, "self": 25.999447167046128 }, "communicator.exchange": { "total": 1448.4944134059701, "count": 63460, "is_parallel": true, "self": 1448.4944134059701 }, "steps_from_proto": { "total": 142.84208620702202, "count": 63460, "is_parallel": true, "self": 29.664670737411598, "children": { "_process_rank_one_or_two_observation": { "total": 113.17741546961042, "count": 507680, "is_parallel": true, "self": 113.17741546961042 } } } } } } } } } } }, "trainer_advance": { "total": 1129.0503328389614, "count": 63461, "self": 4.185184138029854, "children": { "process_trajectory": { "total": 143.7680866499236, "count": 63461, "self": 143.37332115392428, "children": { "RLTrainer._checkpoint": { "total": 0.39476549599930877, "count": 2, "self": 0.39476549599930877 } } }, "_update_policy": { "total": 981.0970620510079, "count": 443, "self": 438.14140655695746, "children": { "TorchPPOOptimizer.update": { "total": 542.9556554940505, "count": 22767, "self": 542.9556554940505 } } } } } } }, "trainer_threads": { "total": 1.1370002539479174e-06, "count": 1, "self": 1.1370002539479174e-06 }, "TrainerController._save_models": { "total": 0.11500749300012103, "count": 1, "self": 0.0017658930000834516, "children": { "RLTrainer._checkpoint": { "total": 0.11324160000003758, "count": 1, "self": 0.11324160000003758 } } } } } } }