{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11944945156574249, "min": 0.11358385533094406, "max": 1.3361033201217651, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3602.595458984375, "min": 3383.383544921875, "max": 40532.03125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 29975.0, "max": 2999965.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 29975.0, "max": 2999965.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.776624858379364, "min": -0.10249456018209457, "max": 0.8700633645057678, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 229.10433959960938, "min": -24.393705368041992, "max": 271.45977783203125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02705737203359604, "min": -0.0199726652354002, "max": 0.3841193914413452, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.981925010681152, "min": -5.292756080627441, "max": 92.95689392089844, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07030777303544573, "min": 0.0628793473998039, "max": 0.07355644507118583, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.054616595531686, "min": 0.5148951154983008, "max": 1.0573544614211035, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01445784309986991, "min": 0.001990515664903367, "max": 0.017782053084119877, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21686764649804866, "min": 0.02587670364374377, "max": 0.2489487431776783, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4910995029999977e-06, "min": 1.4910995029999977e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2366492544999967e-05, "min": 2.2366492544999967e-05, "max": 0.0040724449425184, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049700000000003, "min": 0.10049700000000003, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074550000000004, "min": 1.3962282666666668, "max": 2.8574816, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.965029999999993e-05, "min": 5.965029999999993e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000894754499999999, "min": 0.000894754499999999, "max": 0.13576241184, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009918417781591415, "min": 0.009446214884519577, "max": 0.5738606452941895, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14877626299858093, "min": 0.1353917419910431, "max": 4.017024517059326, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 215.36879432624113, "min": 203.83448275862068, "max": 986.7058823529412, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30367.0, "min": 16774.0, "max": 32859.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.742072325120581, "min": -0.8700000485953163, "max": 1.796165507209712, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.63219784200191, "min": -26.347601659595966, "max": 260.44399854540825, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.742072325120581, "min": -0.8700000485953163, "max": 1.796165507209712, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.63219784200191, "min": -26.347601659595966, "max": 260.44399854540825, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022262255893762187, "min": 0.021579025778016236, "max": 10.155288637560957, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1389780810204684, "min": 2.9726999542617705, "max": 172.63990683853626, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697697924", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697705450" }, "total": 7526.182461605001, "count": 1, "self": 0.6326489260009112, "children": { "run_training.setup": { "total": 0.048939825999923414, "count": 1, "self": 0.048939825999923414 }, "TrainerController.start_learning": { "total": 7525.500872853, "count": 1, "self": 4.4395564680608, "children": { "TrainerController._reset_env": { "total": 7.28454001700004, "count": 1, "self": 7.28454001700004 }, "TrainerController.advance": { "total": 7513.646333574939, "count": 195421, "self": 4.384497697824372, "children": { "env_step": { "total": 5583.476512425045, "count": 195421, "self": 5200.603654189745, "children": { "SubprocessEnvManager._take_step": { "total": 380.30148921301134, "count": 195421, "self": 14.169571088080033, "children": { "TorchPolicy.evaluate": { "total": 366.1319181249313, "count": 187554, "self": 366.1319181249313 } } }, "workers": { "total": 2.5713690222887635, "count": 195421, "self": 0.0, "children": { "worker_root": { "total": 7511.006855763873, "count": 195421, "is_parallel": true, "self": 2676.7122494620207, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004688579999992726, "count": 1, "is_parallel": true, "self": 0.003345408000086536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013431719999061897, "count": 8, "is_parallel": true, "self": 0.0013431719999061897 } } }, "UnityEnvironment.step": { "total": 0.07684060300005058, "count": 1, "is_parallel": true, "self": 0.000678286000152184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005436259999669346, "count": 1, "is_parallel": true, "self": 0.0005436259999669346 }, "communicator.exchange": { "total": 0.0735342949999449, "count": 1, "is_parallel": true, "self": 0.0735342949999449 }, "steps_from_proto": { "total": 0.0020843959999865547, "count": 1, "is_parallel": true, "self": 0.00041991500006588467, "children": { "_process_rank_one_or_two_observation": { "total": 0.00166448099992067, "count": 8, "is_parallel": true, "self": 0.00166448099992067 } } } } } } }, "UnityEnvironment.step": { "total": 4834.294606301853, "count": 195420, "is_parallel": true, "self": 108.61068526875897, "children": { "UnityEnvironment._generate_step_input": { "total": 74.2005608505965, "count": 195420, "is_parallel": true, "self": 74.2005608505965 }, "communicator.exchange": { "total": 4343.343110791254, "count": 195420, "is_parallel": true, "self": 4343.343110791254 }, "steps_from_proto": { "total": 308.1402493912434, "count": 195420, "is_parallel": true, "self": 62.05968054683774, "children": { "_process_rank_one_or_two_observation": { "total": 246.08056884440566, "count": 1563360, "is_parallel": true, "self": 246.08056884440566 } } } } } } } } } } }, "trainer_advance": { "total": 1925.7853234520694, "count": 195421, "self": 8.635148375960853, "children": { "process_trajectory": { "total": 375.37493168711126, "count": 195421, "self": 374.69939377211176, "children": { "RLTrainer._checkpoint": { "total": 0.6755379149994951, "count": 6, "self": 0.6755379149994951 } } }, "_update_policy": { "total": 1541.7752433889973, "count": 1408, "self": 928.4843724531396, "children": { "TorchPPOOptimizer.update": { "total": 613.2908709358577, "count": 68340, "self": 613.2908709358577 } } } } } } }, "trainer_threads": { "total": 1.6520007193321362e-06, "count": 1, "self": 1.6520007193321362e-06 }, "TrainerController._save_models": { "total": 0.1304411410001194, "count": 1, "self": 0.0020765829995070817, "children": { "RLTrainer._checkpoint": { "total": 0.1283645580006123, "count": 1, "self": 0.1283645580006123 } } } } } } }