{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3694307804107666, "min": 0.3468623459339142, "max": 1.4501878023147583, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11006.08203125, "min": 10422.51953125, "max": 43992.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44619765877723694, "min": -0.09007268399000168, "max": 0.44619765877723694, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.24237823486328, "min": -21.707517623901367, "max": 119.62428283691406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13129499554634094, "min": -0.05074075236916542, "max": 0.477482408285141, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 34.793174743652344, "min": -13.44629955291748, "max": 113.163330078125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06689265700697432, "min": 0.06535915161865496, "max": 0.07235663025863326, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9364971980976405, "min": 0.5000087641726179, "max": 1.065577743966452, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018677488933636115, "min": 0.001203853121733604, "max": 0.018677488933636115, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26148484507090564, "min": 0.015650090582536854, "max": 0.26148484507090564, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.722654568671433e-06, "min": 7.722654568671433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010811716396140006, "min": 0.00010811716396140006, "max": 0.0035086685304438997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257418571428574, "min": 0.10257418571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360386000000003, "min": 1.3886848, "max": 2.5695561000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000267161152857143, "min": 0.000267161152857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003740256140000002, "min": 0.003740256140000002, "max": 0.11697865438999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012549474835395813, "min": 0.012549474835395813, "max": 0.3862326145172119, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17569264769554138, "min": 0.1693027913570404, "max": 2.7036283016204834, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 436.2957746478873, "min": 423.63380281690144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30977.0, "min": 15984.0, "max": 32957.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4509971673849602, "min": -1.0000000521540642, "max": 1.491822513895975, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.02079888433218, "min": -28.498601645231247, "max": 105.91939848661423, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4509971673849602, "min": -1.0000000521540642, "max": 1.491822513895975, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.02079888433218, "min": -28.498601645231247, "max": 105.91939848661423, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05678280049825946, "min": 0.05678280049825946, "max": 7.451136095449328, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.031578835376422, "min": 3.935806885783677, "max": 119.21817752718925, "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": "1695332361", "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": "1695334914" }, "total": 2553.0365297460003, "count": 1, "self": 0.685659332000796, "children": { "run_training.setup": { "total": 0.042566842000042016, "count": 1, "self": 0.042566842000042016 }, "TrainerController.start_learning": { "total": 2552.3083035719997, "count": 1, "self": 2.0619442620532027, "children": { "TrainerController._reset_env": { "total": 4.220468095000115, "count": 1, "self": 4.220468095000115 }, "TrainerController.advance": { "total": 2545.8486676839457, "count": 63489, "self": 1.9730237529188344, "children": { "env_step": { "total": 1804.7609709870353, "count": 63489, "self": 1657.2398314270035, "children": { "SubprocessEnvManager._take_step": { "total": 146.2938287220602, "count": 63489, "self": 6.127164634068322, "children": { "TorchPolicy.evaluate": { "total": 140.16666408799188, "count": 62559, "self": 140.16666408799188 } } }, "workers": { "total": 1.2273108379715723, "count": 63489, "self": 0.0, "children": { "worker_root": { "total": 2545.2873605630302, "count": 63489, "is_parallel": true, "self": 1040.4118286790072, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026375630000075034, "count": 1, "is_parallel": true, "self": 0.0009338599995771801, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017037030004303233, "count": 8, "is_parallel": true, "self": 0.0017037030004303233 } } }, "UnityEnvironment.step": { "total": 0.05359686600013447, "count": 1, "is_parallel": true, "self": 0.0006114000000252418, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005518670000128623, "count": 1, "is_parallel": true, "self": 0.0005518670000128623 }, "communicator.exchange": { "total": 0.04935094699999354, "count": 1, "is_parallel": true, "self": 0.04935094699999354 }, "steps_from_proto": { "total": 0.0030826520001028257, "count": 1, "is_parallel": true, "self": 0.00041018900014933024, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026724629999534955, "count": 8, "is_parallel": true, "self": 0.0026724629999534955 } } } } } } }, "UnityEnvironment.step": { "total": 1504.875531884023, "count": 63488, "is_parallel": true, "self": 39.17778449585899, "children": { "UnityEnvironment._generate_step_input": { "total": 27.72196038906759, "count": 63488, "is_parallel": true, "self": 27.72196038906759 }, "communicator.exchange": { "total": 1308.972107115054, "count": 63488, "is_parallel": true, "self": 1308.972107115054 }, "steps_from_proto": { "total": 129.0036798840424, "count": 63488, "is_parallel": true, "self": 26.581838162081567, "children": { "_process_rank_one_or_two_observation": { "total": 102.42184172196085, "count": 507904, "is_parallel": true, "self": 102.42184172196085 } } } } } } } } } } }, "trainer_advance": { "total": 739.1146729439915, "count": 63489, "self": 3.7960636060511206, "children": { "process_trajectory": { "total": 135.21909889393396, "count": 63489, "self": 134.9331739439333, "children": { "RLTrainer._checkpoint": { "total": 0.28592495000066265, "count": 2, "self": 0.28592495000066265 } } }, "_update_policy": { "total": 600.0995104440065, "count": 454, "self": 393.4001079460131, "children": { "TorchPPOOptimizer.update": { "total": 206.69940249799333, "count": 22791, "self": 206.69940249799333 } } } } } } }, "trainer_threads": { "total": 1.5260002328432165e-06, "count": 1, "self": 1.5260002328432165e-06 }, "TrainerController._save_models": { "total": 0.1772220050006581, "count": 1, "self": 0.0021279760003380943, "children": { "RLTrainer._checkpoint": { "total": 0.17509402900032, "count": 1, "self": 0.17509402900032 } } } } } } }