{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23551686108112335, "min": 0.23551686108112335, "max": 1.428954005241394, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 7065.505859375, "min": 7065.505859375, "max": 43348.75, "count": 50 }, "Pyramids.Step.mean": { "value": 1499985.0, "min": 29889.0, "max": 1499985.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499985.0, "min": 29889.0, "max": 1499985.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7679235339164734, "min": -0.10165933519601822, "max": 0.7862588763237, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 227.30535888671875, "min": -24.49989891052246, "max": 234.30514526367188, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004572571255266666, "min": -0.011763223446905613, "max": 0.7160788774490356, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3534810543060303, "min": -3.434861183166504, "max": 169.710693359375, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06972586715901928, "min": 0.06600348931847382, "max": 0.07494587959867538, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9761621402262699, "min": 0.5246211571907277, "max": 1.0909137852289075, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01428520691971404, "min": 0.0003765190338286428, "max": 0.01898136554900434, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19999289687599656, "min": 0.0045182284059437135, "max": 0.23602124210932138, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001515544851961405, "min": 0.0001515544851961405, "max": 0.00029838354339596195, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0021217627927459667, "min": 0.0020886848037717336, "max": 0.0038474494175169335, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15051814523809526, "min": 0.15051814523809526, "max": 0.19946118095238097, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1072540333333336, "min": 1.3962282666666668, "max": 2.7824830666666664, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.005056762709285714, "min": 0.005056762709285714, "max": 0.009946171977142856, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.07079467793, "min": 0.06962320384, "max": 0.12827005836, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008640543557703495, "min": 0.00850665383040905, "max": 0.6313191652297974, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12096761167049408, "min": 0.119093157351017, "max": 4.419234275817871, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.1709401709402, "min": 238.1639344262295, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30557.0, "min": 16816.0, "max": 32145.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.70463075214981, "min": -0.9999871489501768, "max": 1.742260641983298, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.4417980015278, "min": -31.998801678419113, "max": 212.55579832196236, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.70463075214981, "min": -0.9999871489501768, "max": 1.742260641983298, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.4417980015278, "min": -31.998801678419113, "max": 212.55579832196236, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02336091256643741, "min": 0.023257140563056635, "max": 12.748844596831237, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.733226770273177, "min": 2.60449622804299, "max": 216.73035814613104, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717295843", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717300939" }, "total": 5096.572073262, "count": 1, "self": 10.016513268999915, "children": { "run_training.setup": { "total": 0.06835060299999896, "count": 1, "self": 0.06835060299999896 }, "TrainerController.start_learning": { "total": 5086.48720939, "count": 1, "self": 3.6904761299338134, "children": { "TrainerController._reset_env": { "total": 3.5695399789999556, "count": 1, "self": 3.5695399789999556 }, "TrainerController.advance": { "total": 5079.135129145066, "count": 96963, "self": 3.8947078281671565, "children": { "env_step": { "total": 3470.3674948899925, "count": 96963, "self": 3233.5374938249865, "children": { "SubprocessEnvManager._take_step": { "total": 234.63855389190542, "count": 96963, "self": 10.72977770082855, "children": { "TorchPolicy.evaluate": { "total": 223.90877619107687, "count": 94445, "self": 223.90877619107687 } } }, "workers": { "total": 2.1914471731006415, "count": 96962, "self": 0.0, "children": { "worker_root": { "total": 5073.441598668095, "count": 96962, "is_parallel": true, "self": 2122.2772730609995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006185402000028262, "count": 1, "is_parallel": true, "self": 0.004523844000118515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016615579999097463, "count": 8, "is_parallel": true, "self": 0.0016615579999097463 } } }, "UnityEnvironment.step": { "total": 0.06134193499997309, "count": 1, "is_parallel": true, "self": 0.0007351730000664247, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005265849999886996, "count": 1, "is_parallel": true, "self": 0.0005265849999886996 }, "communicator.exchange": { "total": 0.058123232999946595, "count": 1, "is_parallel": true, "self": 0.058123232999946595 }, "steps_from_proto": { "total": 0.0019569439999713723, "count": 1, "is_parallel": true, "self": 0.0004011329998547808, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015558110001165915, "count": 8, "is_parallel": true, "self": 0.0015558110001165915 } } } } } } }, "UnityEnvironment.step": { "total": 2951.1643256070956, "count": 96961, "is_parallel": true, "self": 76.67513662533247, "children": { "UnityEnvironment._generate_step_input": { "total": 47.331383175808014, "count": 96961, "is_parallel": true, "self": 47.331383175808014 }, "communicator.exchange": { "total": 2629.3576256059255, "count": 96961, "is_parallel": true, "self": 2629.3576256059255 }, "steps_from_proto": { "total": 197.80018020002933, "count": 96961, "is_parallel": true, "self": 42.47767654322058, "children": { "_process_rank_one_or_two_observation": { "total": 155.32250365680875, "count": 775688, "is_parallel": true, "self": 155.32250365680875 } } } } } } } } } } }, "trainer_advance": { "total": 1604.872926426906, "count": 96962, "self": 6.674158850794356, "children": { "process_trajectory": { "total": 249.86062613011893, "count": 96962, "self": 249.46366886611952, "children": { "RLTrainer._checkpoint": { "total": 0.3969572639994112, "count": 3, "self": 0.3969572639994112 } } }, "_update_policy": { "total": 1348.3381414459927, "count": 686, "self": 552.8368815839934, "children": { "TorchPPOOptimizer.update": { "total": 795.5012598619993, "count": 34494, "self": 795.5012598619993 } } } } } } }, "trainer_threads": { "total": 1.5260002328432165e-06, "count": 1, "self": 1.5260002328432165e-06 }, "TrainerController._save_models": { "total": 0.09206261000053928, "count": 1, "self": 0.002072358000987151, "children": { "RLTrainer._checkpoint": { "total": 0.08999025199955213, "count": 1, "self": 0.08999025199955213 } } } } } } }