{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27937474846839905, "min": 0.27937474846839905, "max": 1.4864025115966797, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8341.0126953125, "min": 8341.0126953125, "max": 45091.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6360002756118774, "min": -0.07909811288118362, "max": 0.6914540529251099, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.53207397460938, "min": -19.062644958496094, "max": 200.16183471679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.046479370445013046, "min": -0.030678479000926018, "max": 0.7684559226036072, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.339579582214355, "min": -8.651330947875977, "max": 182.12405395507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06791016161566533, "min": 0.06500845303826697, "max": 0.07495118086289104, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9507422626193147, "min": 0.4984966723663845, "max": 1.0418885283870623, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017873680092244677, "min": 0.0010603249835833338, "max": 0.03519514988248078, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25023152129142545, "min": 0.010603249835833337, "max": 0.2559232931406073, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2780332883071435e-06, "min": 7.2780332883071435e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010189246603630001, "min": 0.00010189246603630001, "max": 0.0036331060889647, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242597857142856, "min": 0.10242597857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339636999999998, "min": 1.3886848, "max": 2.6175297999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025235525928571427, "min": 0.00025235525928571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00353297363, "min": 0.00353297363, "max": 0.12112242647000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01539673376828432, "min": 0.01539673376828432, "max": 0.8846275210380554, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21555426716804504, "min": 0.21555426716804504, "max": 6.192392826080322, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.9906542056075, "min": 272.5221238938053, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31243.0, "min": 15984.0, "max": 32700.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6519177384744181, "min": -1.0000000521540642, "max": 1.6934838568972004, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.75519801676273, "min": -28.961401589214802, "max": 189.20319779217243, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6519177384744181, "min": -1.0000000521540642, "max": 1.6934838568972004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.75519801676273, "min": -28.961401589214802, "max": 189.20319779217243, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04657390878468352, "min": 0.04487593098909784, "max": 20.673142137005925, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.983408239961136, "min": 4.6222208918770775, "max": 330.7702741920948, "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": "1691884207", "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": "1691886577" }, "total": 2370.651076368, "count": 1, "self": 0.4784829579994039, "children": { "run_training.setup": { "total": 0.0415478360000634, "count": 1, "self": 0.0415478360000634 }, "TrainerController.start_learning": { "total": 2370.1310455740004, "count": 1, "self": 1.4355088101028741, "children": { "TrainerController._reset_env": { "total": 3.9749030279999715, "count": 1, "self": 3.9749030279999715 }, "TrainerController.advance": { "total": 2364.623899872897, "count": 64335, "self": 1.497655004904118, "children": { "env_step": { "total": 1705.6588050719565, "count": 64335, "self": 1591.0402603098537, "children": { "SubprocessEnvManager._take_step": { "total": 113.72062795105558, "count": 64335, "self": 5.0434466911256095, "children": { "TorchPolicy.evaluate": { "total": 108.67718125992997, "count": 62573, "self": 108.67718125992997 } } }, "workers": { "total": 0.8979168110472528, "count": 64335, "self": 0.0, "children": { "worker_root": { "total": 2364.9838632238097, "count": 64335, "is_parallel": true, "self": 894.9529863538264, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020070029995622463, "count": 1, "is_parallel": true, "self": 0.0006094219997976325, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013975809997646138, "count": 8, "is_parallel": true, "self": 0.0013975809997646138 } } }, "UnityEnvironment.step": { "total": 0.054058198999882734, "count": 1, "is_parallel": true, "self": 0.0005918010001551011, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000505629000144836, "count": 1, "is_parallel": true, "self": 0.000505629000144836 }, "communicator.exchange": { "total": 0.05098587199972826, "count": 1, "is_parallel": true, "self": 0.05098587199972826 }, "steps_from_proto": { "total": 0.0019748969998545363, "count": 1, "is_parallel": true, "self": 0.0003918839984180522, "children": { "_process_rank_one_or_two_observation": { "total": 0.001583013001436484, "count": 8, "is_parallel": true, "self": 0.001583013001436484 } } } } } } }, "UnityEnvironment.step": { "total": 1470.0308768699833, "count": 64334, "is_parallel": true, "self": 35.34004827807803, "children": { "UnityEnvironment._generate_step_input": { "total": 24.49879130602858, "count": 64334, "is_parallel": true, "self": 24.49879130602858 }, "communicator.exchange": { "total": 1296.6050484449233, "count": 64334, "is_parallel": true, "self": 1296.6050484449233 }, "steps_from_proto": { "total": 113.58698884095338, "count": 64334, "is_parallel": true, "self": 22.849135055833358, "children": { "_process_rank_one_or_two_observation": { "total": 90.73785378512002, "count": 514672, "is_parallel": true, "self": 90.73785378512002 } } } } } } } } } } }, "trainer_advance": { "total": 657.4674397960362, "count": 64335, "self": 2.7400245271428503, "children": { "process_trajectory": { "total": 120.00852051789661, "count": 64335, "self": 119.79305636089612, "children": { "RLTrainer._checkpoint": { "total": 0.21546415700049693, "count": 2, "self": 0.21546415700049693 } } }, "_update_policy": { "total": 534.7188947509967, "count": 452, "self": 347.6193613950145, "children": { "TorchPPOOptimizer.update": { "total": 187.0995333559822, "count": 22767, "self": 187.0995333559822 } } } } } } }, "trainer_threads": { "total": 1.052000698109623e-06, "count": 1, "self": 1.052000698109623e-06 }, "TrainerController._save_models": { "total": 0.09673281100003805, "count": 1, "self": 0.0014729759996043867, "children": { "RLTrainer._checkpoint": { "total": 0.09525983500043367, "count": 1, "self": 0.09525983500043367 } } } } } } }