{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.612159252166748, "min": 0.584998607635498, "max": 1.4656339883804321, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18266.83203125, "min": 17409.55859375, "max": 44461.47265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2581080198287964, "min": -0.0998375415802002, "max": 0.2581080198287964, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 66.07565307617188, "min": -23.961009979248047, "max": 66.07565307617188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.062075160443782806, "min": -0.07101096212863922, "max": 0.5369735956192017, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -15.891241073608398, "min": -18.17880630493164, "max": 127.26274108886719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07146817984499244, "min": 0.06456436518333032, "max": 0.07369897491605962, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0720226976748866, "min": 0.5137358177777771, "max": 1.072317981282158, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010919580027338172, "min": 0.0001375981774878372, "max": 0.012035735199918107, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16379370041007257, "min": 0.0017887763073418837, "max": 0.1685002927988535, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.46667751114e-06, "min": 7.46667751114e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011200016266709999, "min": 0.00011200016266709999, "max": 0.0033758899747033996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248886, "min": 0.10248886, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373329, "min": 1.3886848, "max": 2.4252966000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025863711399999996, "min": 0.00025863711399999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038795567099999995, "min": 0.0038795567099999995, "max": 0.11254713034000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01331599336117506, "min": 0.01331599336117506, "max": 0.670852780342102, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19973990321159363, "min": 0.18974359333515167, "max": 4.695969581604004, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 622.9583333333334, "min": 555.94, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29902.0, "min": 15984.0, "max": 32666.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9185707978904247, "min": -1.0000000521540642, "max": 1.0188448689117724, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.09139829874039, "min": -30.994201600551605, "max": 49.923398576676846, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9185707978904247, "min": -1.0000000521540642, "max": 1.0188448689117724, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.09139829874039, "min": -30.994201600551605, "max": 49.923398576676846, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08604963786153046, "min": 0.08541505734319799, "max": 15.823239730671048, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.130382617353462, "min": 4.130382617353462, "max": 253.17183569073677, "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": "1737674643", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/julio/miniconda3/envs/ml_agents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737676023" }, "total": 1262.581337831, "count": 1, "self": 0.2676031709997915, "children": { "run_training.setup": { "total": 0.009494720000020607, "count": 1, "self": 0.009494720000020607 }, "TrainerController.start_learning": { "total": 1262.3042399400001, "count": 1, "self": 0.5932870680039741, "children": { "TrainerController._reset_env": { "total": 2.7882528430000093, "count": 1, "self": 2.7882528430000093 }, "TrainerController.advance": { "total": 1258.8733368849962, "count": 63373, "self": 0.5349831770299716, "children": { "env_step": { "total": 899.3790819669862, "count": 63373, "self": 763.5939723500092, "children": { "SubprocessEnvManager._take_step": { "total": 135.39790926198924, "count": 63373, "self": 1.8320313669745474, "children": { "TorchPolicy.evaluate": { "total": 133.5658778950147, "count": 62565, "self": 133.5658778950147 } } }, "workers": { "total": 0.38720035498784, "count": 63373, "self": 0.0, "children": { "worker_root": { "total": 1260.4012296610158, "count": 63373, "is_parallel": true, "self": 535.687552196001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009919574000036846, "count": 1, "is_parallel": true, "self": 0.009212724000065009, "children": { "_process_rank_one_or_two_observation": { "total": 0.000706849999971837, "count": 8, "is_parallel": true, "self": 0.000706849999971837 } } }, "UnityEnvironment.step": { "total": 0.021521519000032185, "count": 1, "is_parallel": true, "self": 0.00012278200006221596, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014265499999055464, "count": 1, "is_parallel": true, "self": 0.00014265499999055464 }, "communicator.exchange": { "total": 0.020820978999950057, "count": 1, "is_parallel": true, "self": 0.020820978999950057 }, "steps_from_proto": { "total": 0.00043510300002935764, "count": 1, "is_parallel": true, "self": 0.00013528099998438847, "children": { "_process_rank_one_or_two_observation": { "total": 0.00029982200004496917, "count": 8, "is_parallel": true, "self": 0.00029982200004496917 } } } } } } }, "UnityEnvironment.step": { "total": 724.7136774650148, "count": 63372, "is_parallel": true, "self": 6.707059789005598, "children": { "UnityEnvironment._generate_step_input": { "total": 4.8336709330250756, "count": 63372, "is_parallel": true, "self": 4.8336709330250756 }, "communicator.exchange": { "total": 695.0841640119871, "count": 63372, "is_parallel": true, "self": 695.0841640119871 }, "steps_from_proto": { "total": 18.08878273099714, "count": 63372, "is_parallel": true, "self": 4.365711551029278, "children": { "_process_rank_one_or_two_observation": { "total": 13.72307117996786, "count": 506976, "is_parallel": true, "self": 13.72307117996786 } } } } } } } } } } }, "trainer_advance": { "total": 358.9592717409801, "count": 63373, "self": 1.1316833159880844, "children": { "process_trajectory": { "total": 63.40014608499115, "count": 63373, "self": 63.25563587199093, "children": { "RLTrainer._checkpoint": { "total": 0.14451021300021694, "count": 2, "self": 0.14451021300021694 } } }, "_update_policy": { "total": 294.4274423400009, "count": 445, "self": 129.6524758549943, "children": { "TorchPPOOptimizer.update": { "total": 164.7749664850066, "count": 22833, "self": 164.7749664850066 } } } } } } }, "trainer_threads": { "total": 5.510000846697949e-07, "count": 1, "self": 5.510000846697949e-07 }, "TrainerController._save_models": { "total": 0.04936259299984158, "count": 1, "self": 0.0006726859999162116, "children": { "RLTrainer._checkpoint": { "total": 0.04868990699992537, "count": 1, "self": 0.04868990699992537 } } } } } } }