{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8949658870697021, "min": 0.8949658870697021, "max": 1.5154129266738892, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 26806.017578125, "min": 26806.017578125, "max": 45971.56640625, "count": 6 }, "Pyramids.Step.mean": { "value": 179967.0, "min": 29952.0, "max": 179967.0, "count": 6 }, "Pyramids.Step.sum": { "value": 179967.0, "min": 29952.0, "max": 179967.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07629839330911636, "min": -0.12691165506839752, "max": 0.09217556565999985, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -18.311614990234375, "min": -30.585708618164062, "max": 21.845609664916992, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0802893415093422, "min": 0.07011277973651886, "max": 0.21157467365264893, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.269441604614258, "min": 16.96729278564453, "max": 51.201072692871094, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07112719050467846, "min": 0.06595206873635336, "max": 0.07112719050467846, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9957806670654984, "min": 0.4902688855748227, "max": 0.9957806670654984, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00022647540521970132, "min": 0.00022647540521970132, "max": 0.007850787172704187, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0031706556730758183, "min": 0.0031706556730758183, "max": 0.05495551020892932, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00025051025935372856, "min": 0.00025051025935372856, "max": 0.00029515063018788575, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0035071436309521997, "min": 0.0020660544113152, "max": 0.0035071436309521997, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18350341428571423, "min": 0.18350341428571423, "max": 0.19838354285714285, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5690477999999994, "min": 1.3886848, "max": 2.5690477999999994, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.008351991087142857, "min": 0.008351991087142857, "max": 0.00983851593142857, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.11692787522, "min": 0.06886961152, "max": 0.11692787522, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.04177739843726158, "min": 0.04177739843726158, "max": 0.30218276381492615, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5848835706710815, "min": 0.5848835706710815, "max": 2.11527943611145, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 949.7272727272727, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 33084.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9997806957652492, "min": -1.0000000521540642, "max": -0.7926938023883849, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.993201568722725, "min": -30.993201568722725, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9997806957652492, "min": -1.0000000521540642, "max": -0.7926938023883849, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.993201568722725, "min": -30.993201568722725, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.4470845099778906, "min": 0.4470845099778906, "max": 5.753728229552507, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 13.859619809314609, "min": 13.859619809314609, "max": 92.05965167284012, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676822497", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.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": "1676822906" }, "total": 409.6301802659998, "count": 1, "self": 0.24925018999965687, "children": { "run_training.setup": { "total": 0.11447417500016854, "count": 1, "self": 0.11447417500016854 }, "TrainerController.start_learning": { "total": 409.266455901, "count": 1, "self": 0.2516374949709643, "children": { "TrainerController._reset_env": { "total": 7.126099874000147, "count": 1, "self": 7.126099874000147 }, "TrainerController.advance": { "total": 401.72199558902844, "count": 12904, "self": 0.26765944403950925, "children": { "env_step": { "total": 256.3840074759935, "count": 12904, "self": 233.57741305196805, "children": { "SubprocessEnvManager._take_step": { "total": 22.655631962006737, "count": 12904, "self": 0.9246146210016377, "children": { "TorchPolicy.evaluate": { "total": 21.7310173410051, "count": 12860, "self": 7.084795019988633, "children": { "TorchPolicy.sample_actions": { "total": 14.646222321016467, "count": 12860, "self": 14.646222321016467 } } } } }, "workers": { "total": 0.1509624620186969, "count": 12904, "self": 0.0, "children": { "worker_root": { "total": 407.2673712310127, "count": 12904, "is_parallel": true, "self": 195.58804944003555, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017852529999800026, "count": 1, "is_parallel": true, "self": 0.0006510959997285681, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011341570002514345, "count": 8, "is_parallel": true, "self": 0.0011341570002514345 } } }, "UnityEnvironment.step": { "total": 0.056768612000041685, "count": 1, "is_parallel": true, "self": 0.0005360960001326021, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004486670000005688, "count": 1, "is_parallel": true, "self": 0.0004486670000005688 }, "communicator.exchange": { "total": 0.05416347599998517, "count": 1, "is_parallel": true, "self": 0.05416347599998517 }, "steps_from_proto": { "total": 0.0016203729999233474, "count": 1, "is_parallel": true, "self": 0.000408205000212547, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012121679997108004, "count": 8, "is_parallel": true, "self": 0.0012121679997108004 } } } } } } }, "UnityEnvironment.step": { "total": 211.67932179097716, "count": 12903, "is_parallel": true, "self": 6.231604727021249, "children": { "UnityEnvironment._generate_step_input": { "total": 4.462146315977861, "count": 12903, "is_parallel": true, "self": 4.462146315977861 }, "communicator.exchange": { "total": 182.48206493799012, "count": 12903, "is_parallel": true, "self": 182.48206493799012 }, "steps_from_proto": { "total": 18.503505809987928, "count": 12903, "is_parallel": true, "self": 4.277607428103465, "children": { "_process_rank_one_or_two_observation": { "total": 14.225898381884463, "count": 103224, "is_parallel": true, "self": 14.225898381884463 } } } } } } } } } } }, "trainer_advance": { "total": 145.07032866899544, "count": 12904, "self": 0.35288276498704363, "children": { "process_trajectory": { "total": 30.30100435001009, "count": 12904, "self": 30.30100435001009 }, "_update_policy": { "total": 114.41644155399831, "count": 78, "self": 44.327122369999415, "children": { "TorchPPOOptimizer.update": { "total": 70.0893191839989, "count": 4692, "self": 70.0893191839989 } } } } } } }, "trainer_threads": { "total": 1.6070002857304644e-06, "count": 1, "self": 1.6070002857304644e-06 }, "TrainerController._save_models": { "total": 0.16672133600013694, "count": 1, "self": 0.001956309999968653, "children": { "RLTrainer._checkpoint": { "total": 0.1647650260001683, "count": 1, "self": 0.1647650260001683 } } } } } } }