{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5099601149559021, "min": 0.4887774586677551, "max": 1.4645769596099854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15306.962890625, "min": 14653.1015625, "max": 44429.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29927.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29927.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5280778408050537, "min": -0.10568121075630188, "max": 0.5280778408050537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.63717651367188, "min": -25.459821701049805, "max": 143.63717651367188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.011786708608269691, "min": -0.011786708608269691, "max": 0.2948857545852661, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.2059848308563232, "min": -3.2059848308563232, "max": 71.36235046386719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0705182091421615, "min": 0.06483767752143352, "max": 0.07386943292155472, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0577731371324226, "min": 0.5594284403680201, "max": 1.081010602501349, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01566761583310485, "min": 7.761746620833927e-05, "max": 0.01566761583310485, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23501423749657274, "min": 0.0010090270607084105, "max": 0.23501423749657274, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.427257524280001e-06, "min": 7.427257524280001e-06, "max": 0.00029484281421906253, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011140886286420001, "min": 0.00011140886286420001, "max": 0.0033831512722830004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247572, "min": 0.10247572, "max": 0.1982809375, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371358000000002, "min": 1.4775616, "max": 2.5277170000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025732442800000004, "min": 0.00025732442800000004, "max": 0.00982826565625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038598664200000005, "min": 0.0038598664200000005, "max": 0.11279892830000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015123224817216396, "min": 0.015123224817216396, "max": 0.5009323358535767, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22684837877750397, "min": 0.2187887728214264, "max": 4.007458686828613, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.79487179487177, "min": 360.79487179487177, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28142.0, "min": 16470.0, "max": 32587.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5879076822445943, "min": -0.99980005237364, "max": 1.5879076822445943, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.85679921507835, "min": -30.99380162358284, "max": 123.85679921507835, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5879076822445943, "min": -0.99980005237364, "max": 1.5879076822445943, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.85679921507835, "min": -30.99380162358284, "max": 123.85679921507835, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05614397526518681, "min": 0.05614397526518681, "max": 10.187116042656058, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.379230070684571, "min": 4.379230070684571, "max": 173.18097272515297, "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": "1743075308", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743077357" }, "total": 2049.000133754, "count": 1, "self": 0.49328428500029986, "children": { "run_training.setup": { "total": 0.028147644999990007, "count": 1, "self": 0.028147644999990007 }, "TrainerController.start_learning": { "total": 2048.478701824, "count": 1, "self": 1.1733268870439133, "children": { "TrainerController._reset_env": { "total": 3.795504443000027, "count": 1, "self": 3.795504443000027 }, "TrainerController.advance": { "total": 2043.4228211939558, "count": 63577, "self": 1.2912381939577244, "children": { "env_step": { "total": 1377.291438592968, "count": 63577, "self": 1232.822327359896, "children": { "SubprocessEnvManager._take_step": { "total": 143.7668192820122, "count": 63577, "self": 4.335450515077582, "children": { "TorchPolicy.evaluate": { "total": 139.4313687669346, "count": 62562, "self": 139.4313687669346 } } }, "workers": { "total": 0.7022919510598058, "count": 63577, "self": 0.0, "children": { "worker_root": { "total": 2044.009483712992, "count": 63577, "is_parallel": true, "self": 914.9856924339626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006243191000066872, "count": 1, "is_parallel": true, "self": 0.004332949000286135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019102419997807374, "count": 8, "is_parallel": true, "self": 0.0019102419997807374 } } }, "UnityEnvironment.step": { "total": 0.04712546000007478, "count": 1, "is_parallel": true, "self": 0.0005807890000824045, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004427970000051573, "count": 1, "is_parallel": true, "self": 0.0004427970000051573 }, "communicator.exchange": { "total": 0.04442740900003628, "count": 1, "is_parallel": true, "self": 0.04442740900003628 }, "steps_from_proto": { "total": 0.001674464999950942, "count": 1, "is_parallel": true, "self": 0.00048220999985915114, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011922550000917909, "count": 8, "is_parallel": true, "self": 0.0011922550000917909 } } } } } } }, "UnityEnvironment.step": { "total": 1129.0237912790294, "count": 63576, "is_parallel": true, "self": 31.082235176171707, "children": { "UnityEnvironment._generate_step_input": { "total": 22.252937221918614, "count": 63576, "is_parallel": true, "self": 22.252937221918614 }, "communicator.exchange": { "total": 985.0591482809509, "count": 63576, "is_parallel": true, "self": 985.0591482809509 }, "steps_from_proto": { "total": 90.62947059998805, "count": 63576, "is_parallel": true, "self": 17.380722344959963, "children": { "_process_rank_one_or_two_observation": { "total": 73.24874825502809, "count": 508608, "is_parallel": true, "self": 73.24874825502809 } } } } } } } } } } }, "trainer_advance": { "total": 664.84014440703, "count": 63577, "self": 2.371697806926477, "children": { "process_trajectory": { "total": 123.35166316210666, "count": 63577, "self": 123.04053740710674, "children": { "RLTrainer._checkpoint": { "total": 0.3111257549999209, "count": 2, "self": 0.3111257549999209 } } }, "_update_policy": { "total": 539.1167834379969, "count": 453, "self": 295.00248331197963, "children": { "TorchPPOOptimizer.update": { "total": 244.11430012601727, "count": 22761, "self": 244.11430012601727 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.08704835800017463, "count": 1, "self": 0.001484689000335493, "children": { "RLTrainer._checkpoint": { "total": 0.08556366899983914, "count": 1, "self": 0.08556366899983914 } } } } } } }