{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34050318598747253, "min": 0.34050318598747253, "max": 1.3917882442474365, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10231.439453125, "min": 10231.439453125, "max": 42221.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29950.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29950.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6623512506484985, "min": -0.08478499948978424, "max": 0.6809508204460144, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.43246459960938, "min": -20.433185577392578, "max": 199.51858520507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011695773340761662, "min": 0.0017226093914359808, "max": 0.40394869446754456, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3449912071228027, "min": 0.5047245621681213, "max": 96.13978576660156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0647931088556807, "min": 0.0646489717132974, "max": 0.073572663222957, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9071035239795296, "min": 0.6083178795591048, "max": 1.103589948344355, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01532207807905565, "min": 0.0010567516142613803, "max": 0.017456777729857088, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2145090931067791, "min": 0.013737770985397945, "max": 0.2587317506161829, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.574947475050001e-06, "min": 7.574947475050001e-06, "max": 0.00029486920171026667, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010604926465070001, "min": 0.00010604926465070001, "max": 0.003635940188019999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252494999999999, "min": 0.10252494999999999, "max": 0.19828973333333333, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353493, "min": 1.4353493, "max": 2.6119800000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002622425050000001, "min": 0.0002622425050000001, "max": 0.00982914436, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003671395070000001, "min": 0.003671395070000001, "max": 0.12121680200000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011863932013511658, "min": 0.01173480600118637, "max": 0.4767794609069824, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1660950481891632, "min": 0.1642872840166092, "max": 4.291015148162842, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.2718446601942, "min": 277.96190476190475, "max": 991.7741935483871, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30928.0, "min": 17260.0, "max": 32819.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6803087210192265, "min": -0.9280258561334302, "max": 1.7029828373874938, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.07179826498032, "min": -28.768801540136337, "max": 182.74899853020906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6803087210192265, "min": -0.9280258561334302, "max": 1.7029828373874938, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.07179826498032, "min": -28.768801540136337, "max": 182.74899853020906, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03655006798454425, "min": 0.03368786300222079, "max": 9.56843827995989, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7646570024080575, "min": 3.537225615233183, "max": 172.23188903927803, "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": "1684059377", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1684061596" }, "total": 2218.33576221, "count": 1, "self": 0.4883241220004493, "children": { "run_training.setup": { "total": 0.04326836000001322, "count": 1, "self": 0.04326836000001322 }, "TrainerController.start_learning": { "total": 2217.8041697279996, "count": 1, "self": 1.2502792679815684, "children": { "TrainerController._reset_env": { "total": 4.033931236000001, "count": 1, "self": 4.033931236000001 }, "TrainerController.advance": { "total": 2212.4295656810177, "count": 64103, "self": 1.2998243560418814, "children": { "env_step": { "total": 1577.8959774309733, "count": 64103, "self": 1474.4990288549027, "children": { "SubprocessEnvManager._take_step": { "total": 102.64203911303872, "count": 64103, "self": 4.601023134035927, "children": { "TorchPolicy.evaluate": { "total": 98.0410159790028, "count": 62551, "self": 98.0410159790028 } } }, "workers": { "total": 0.7549094630318223, "count": 64103, "self": 0.0, "children": { "worker_root": { "total": 2213.104311142039, "count": 64103, "is_parallel": true, "self": 847.656387979993, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005474859000003107, "count": 1, "is_parallel": true, "self": 0.004050574000018514, "children": { "_process_rank_one_or_two_observation": { "total": 0.001424284999984593, "count": 8, "is_parallel": true, "self": 0.001424284999984593 } } }, "UnityEnvironment.step": { "total": 0.04817116200001692, "count": 1, "is_parallel": true, "self": 0.000585257000011552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004970240000261583, "count": 1, "is_parallel": true, "self": 0.0004970240000261583 }, "communicator.exchange": { "total": 0.04529256899996881, "count": 1, "is_parallel": true, "self": 0.04529256899996881 }, "steps_from_proto": { "total": 0.0017963120000104027, "count": 1, "is_parallel": true, "self": 0.00036980499999117455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014265070000192281, "count": 8, "is_parallel": true, "self": 0.0014265070000192281 } } } } } } }, "UnityEnvironment.step": { "total": 1365.447923162046, "count": 64102, "is_parallel": true, "self": 32.201219808004225, "children": { "UnityEnvironment._generate_step_input": { "total": 22.344287013000155, "count": 64102, "is_parallel": true, "self": 22.344287013000155 }, "communicator.exchange": { "total": 1213.8117447110476, "count": 64102, "is_parallel": true, "self": 1213.8117447110476 }, "steps_from_proto": { "total": 97.090671629994, "count": 64102, "is_parallel": true, "self": 19.627042863029374, "children": { "_process_rank_one_or_two_observation": { "total": 77.46362876696463, "count": 512816, "is_parallel": true, "self": 77.46362876696463 } } } } } } } } } } }, "trainer_advance": { "total": 633.2337638940024, "count": 64103, "self": 2.528721767988145, "children": { "process_trajectory": { "total": 107.09841935801421, "count": 64103, "self": 106.82166575301392, "children": { "RLTrainer._checkpoint": { "total": 0.27675360500029456, "count": 2, "self": 0.27675360500029456 } } }, "_update_policy": { "total": 523.6066227680001, "count": 462, "self": 339.81862560500326, "children": { "TorchPPOOptimizer.update": { "total": 183.78799716299682, "count": 22782, "self": 183.78799716299682 } } } } } } }, "trainer_threads": { "total": 1.1699999049596954e-06, "count": 1, "self": 1.1699999049596954e-06 }, "TrainerController._save_models": { "total": 0.09039237300021341, "count": 1, "self": 0.0014130830004432937, "children": { "RLTrainer._checkpoint": { "total": 0.08897928999977012, "count": 1, "self": 0.08897928999977012 } } } } } } }