{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9120617508888245, "min": 0.9120617508888245, "max": 1.464768886566162, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 27288.88671875, "min": 27288.88671875, "max": 44435.23046875, "count": 16 }, "Pyramids.Step.mean": { "value": 479896.0, "min": 29932.0, "max": 479896.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479896.0, "min": 29932.0, "max": 479896.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0794866755604744, "min": -0.09307115525007248, "max": 0.0794866755604744, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 19.633209228515625, "min": -22.52322006225586, "max": 19.633209228515625, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.1525806188583374, "min": -0.1525806188583374, "max": 0.30635830760002136, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -37.68741226196289, "min": -37.68741226196289, "max": 73.83235168457031, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06788035233505722, "min": 0.06482858696982788, "max": 0.07256317303650647, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9503249326908012, "min": 0.5507658067308973, "max": 1.0768643986375535, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014639852689273824, "min": 0.0013250867306813482, "max": 0.014639852689273824, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20495793764983353, "min": 0.01617370724730821, "max": 0.20495793764983353, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0696107387042858e-05, "min": 2.0696107387042858e-05, "max": 0.0002896845034384999, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002897455034186, "min": 0.0002897455034186, "max": 0.0030857420714193997, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10689867142857143, "min": 0.10689867142857143, "max": 0.19656150000000003, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4965814, "min": 1.4965814, "max": 2.4221996, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0006991772757142858, "min": 0.0006991772757142858, "max": 0.009656493849999998, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00978848186, "min": 0.00978848186, "max": 0.10288520194, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02121802046895027, "min": 0.02121802046895027, "max": 0.47465378046035767, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2970522940158844, "min": 0.2970522940158844, "max": 3.7972302436828613, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 768.1538461538462, "min": 768.1538461538462, "max": 997.03125, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29958.0, "min": 16347.0, "max": 32222.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.40857430757620394, "min": -0.9354500502813607, "max": 0.40857430757620394, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 15.934397995471954, "min": -29.934401609003544, "max": 15.934397995471954, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.40857430757620394, "min": -0.9354500502813607, "max": 0.40857430757620394, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 15.934397995471954, "min": -29.934401609003544, "max": 15.934397995471954, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1693210072684078, "min": 0.1693210072684078, "max": 9.300809071344489, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 6.603519283467904, "min": 6.603519283467904, "max": 158.1137542128563, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697783131", "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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697784137" }, "total": 1006.3937609530003, "count": 1, "self": 0.4881499310004074, "children": { "run_training.setup": { "total": 0.04273510500001976, "count": 1, "self": 0.04273510500001976 }, "TrainerController.start_learning": { "total": 1005.8628759169999, "count": 1, "self": 0.5977895260116384, "children": { "TrainerController._reset_env": { "total": 3.584340658999963, "count": 1, "self": 3.584340658999963 }, "TrainerController.advance": { "total": 1001.6061616179882, "count": 31629, "self": 0.6487785780318518, "children": { "env_step": { "total": 691.1402908209716, "count": 31629, "self": 627.847409748973, "children": { "SubprocessEnvManager._take_step": { "total": 62.9301241919984, "count": 31629, "self": 2.2358143350097635, "children": { "TorchPolicy.evaluate": { "total": 60.69430985698864, "count": 31301, "self": 60.69430985698864 } } }, "workers": { "total": 0.36275688000023365, "count": 31629, "self": 0.0, "children": { "worker_root": { "total": 1003.7252299650388, "count": 31629, "is_parallel": true, "self": 429.3982700500178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001975033999997322, "count": 1, "is_parallel": true, "self": 0.0006030470001405774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013719869998567447, "count": 8, "is_parallel": true, "self": 0.0013719869998567447 } } }, "UnityEnvironment.step": { "total": 0.0511135839999497, "count": 1, "is_parallel": true, "self": 0.0005747039999732806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000496862999852965, "count": 1, "is_parallel": true, "self": 0.000496862999852965 }, "communicator.exchange": { "total": 0.048288321999962136, "count": 1, "is_parallel": true, "self": 0.048288321999962136 }, "steps_from_proto": { "total": 0.001753695000161315, "count": 1, "is_parallel": true, "self": 0.00039873100013210205, "children": { "_process_rank_one_or_two_observation": { "total": 0.001354964000029213, "count": 8, "is_parallel": true, "self": 0.001354964000029213 } } } } } } }, "UnityEnvironment.step": { "total": 574.326959915021, "count": 31628, "is_parallel": true, "self": 16.997994626078253, "children": { "UnityEnvironment._generate_step_input": { "total": 11.886607987981051, "count": 31628, "is_parallel": true, "self": 11.886607987981051 }, "communicator.exchange": { "total": 497.613680516979, "count": 31628, "is_parallel": true, "self": 497.613680516979 }, "steps_from_proto": { "total": 47.8286767839827, "count": 31628, "is_parallel": true, "self": 9.357476240068081, "children": { "_process_rank_one_or_two_observation": { "total": 38.47120054391462, "count": 253024, "is_parallel": true, "self": 38.47120054391462 } } } } } } } } } } }, "trainer_advance": { "total": 309.8170922189847, "count": 31629, "self": 1.126637351983618, "children": { "process_trajectory": { "total": 58.54621388800206, "count": 31629, "self": 58.45991850400196, "children": { "RLTrainer._checkpoint": { "total": 0.08629538400009551, "count": 1, "self": 0.08629538400009551 } } }, "_update_policy": { "total": 250.14424097899905, "count": 220, "self": 149.44919185796903, "children": { "TorchPPOOptimizer.update": { "total": 100.69504912103002, "count": 11397, "self": 100.69504912103002 } } } } } } }, "trainer_threads": { "total": 8.609999895270448e-07, "count": 1, "self": 8.609999895270448e-07 }, "TrainerController._save_models": { "total": 0.07458325300012802, "count": 1, "self": 0.0012606509999386617, "children": { "RLTrainer._checkpoint": { "total": 0.07332260200018936, "count": 1, "self": 0.07332260200018936 } } } } } } }