{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4231332540512085, "min": 0.4115739166736603, "max": 1.4713134765625, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12653.376953125, "min": 12301.12109375, "max": 44633.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4903695285320282, "min": -0.0796075314283371, "max": 0.5660239458084106, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.9479217529297, "min": -19.10580825805664, "max": 158.05557250976562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01585151068866253, "min": 0.006594083271920681, "max": 0.4534107446670532, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.200650215148926, "min": 1.8397492170333862, "max": 107.45834350585938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06799861588626213, "min": 0.06451841492105377, "max": 0.07376564625034791, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9519806224076698, "min": 0.4942031819077314, "max": 1.0452088640110255, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015737092249245115, "min": 0.0013498654579249916, "max": 0.017846962708954736, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22031929148943163, "min": 0.01889811641094988, "max": 0.2498574779253663, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.408426101985714e-06, "min": 7.408426101985714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001037179654278, "min": 0.0001037179654278, "max": 0.0035084750305083992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246944285714285, "min": 0.10246944285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345721999999999, "min": 1.3886848, "max": 2.5694916, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025669734142857146, "min": 0.00025669734142857146, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035937627800000007, "min": 0.0035937627800000007, "max": 0.11697221084000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014637910760939121, "min": 0.014637910760939121, "max": 0.5853918790817261, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20493075251579285, "min": 0.20493075251579285, "max": 4.097743034362793, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.54545454545456, "min": 318.7816091954023, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30226.0, "min": 15984.0, "max": 33307.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4778960842590827, "min": -1.0000000521540642, "max": 1.6794947156780644, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.79799848794937, "min": -26.884001724421978, "max": 159.55199798941612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4778960842590827, "min": -1.0000000521540642, "max": 1.6794947156780644, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.79799848794937, "min": -26.884001724421978, "max": 159.55199798941612, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05924929790697726, "min": 0.0498185669919047, "max": 11.994166266173124, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.562195938837249, "min": 4.402557848894503, "max": 191.90666025877, "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": "1709125439", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709127535" }, "total": 2096.153354951, "count": 1, "self": 0.5850153989999853, "children": { "run_training.setup": { "total": 0.04538046800007578, "count": 1, "self": 0.04538046800007578 }, "TrainerController.start_learning": { "total": 2095.522959084, "count": 1, "self": 1.2918289000122058, "children": { "TrainerController._reset_env": { "total": 2.3945542159999604, "count": 1, "self": 2.3945542159999604 }, "TrainerController.advance": { "total": 2091.750768598987, "count": 63869, "self": 1.3726294459079327, "children": { "env_step": { "total": 1474.7476612050646, "count": 63869, "self": 1346.5294149019055, "children": { "SubprocessEnvManager._take_step": { "total": 127.4235469950645, "count": 63869, "self": 4.589454981045947, "children": { "TorchPolicy.evaluate": { "total": 122.83409201401855, "count": 62573, "self": 122.83409201401855 } } }, "workers": { "total": 0.7946993080945504, "count": 63869, "self": 0.0, "children": { "worker_root": { "total": 2090.6676694950374, "count": 63869, "is_parallel": true, "self": 855.5371090559174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020469259998208145, "count": 1, "is_parallel": true, "self": 0.0006242300005396828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014226959992811317, "count": 8, "is_parallel": true, "self": 0.0014226959992811317 } } }, "UnityEnvironment.step": { "total": 0.05332269699965764, "count": 1, "is_parallel": true, "self": 0.0006682169992018316, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005535640002563014, "count": 1, "is_parallel": true, "self": 0.0005535640002563014 }, "communicator.exchange": { "total": 0.050089495000065654, "count": 1, "is_parallel": true, "self": 0.050089495000065654 }, "steps_from_proto": { "total": 0.0020114210001338506, "count": 1, "is_parallel": true, "self": 0.00038189599945326336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016295250006805873, "count": 8, "is_parallel": true, "self": 0.0016295250006805873 } } } } } } }, "UnityEnvironment.step": { "total": 1235.13056043912, "count": 63868, "is_parallel": true, "self": 34.62861506813442, "children": { "UnityEnvironment._generate_step_input": { "total": 23.947141207052027, "count": 63868, "is_parallel": true, "self": 23.947141207052027 }, "communicator.exchange": { "total": 1080.5847757970523, "count": 63868, "is_parallel": true, "self": 1080.5847757970523 }, "steps_from_proto": { "total": 95.97002836688125, "count": 63868, "is_parallel": true, "self": 18.69738863508701, "children": { "_process_rank_one_or_two_observation": { "total": 77.27263973179424, "count": 510944, "is_parallel": true, "self": 77.27263973179424 } } } } } } } } } } }, "trainer_advance": { "total": 615.6304779480147, "count": 63869, "self": 2.557446473010259, "children": { "process_trajectory": { "total": 122.45471749400485, "count": 63869, "self": 122.25971201900529, "children": { "RLTrainer._checkpoint": { "total": 0.19500547499956156, "count": 2, "self": 0.19500547499956156 } } }, "_update_policy": { "total": 490.6183139809996, "count": 452, "self": 286.19490039804623, "children": { "TorchPPOOptimizer.update": { "total": 204.42341358295334, "count": 22782, "self": 204.42341358295334 } } } } } } }, "trainer_threads": { "total": 1.1350002750987187e-06, "count": 1, "self": 1.1350002750987187e-06 }, "TrainerController._save_models": { "total": 0.08580623400030163, "count": 1, "self": 0.0014424339997276547, "children": { "RLTrainer._checkpoint": { "total": 0.08436380000057397, "count": 1, "self": 0.08436380000057397 } } } } } } }