{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8922141790390015, "min": 0.8922141790390015, "max": 1.4813717603683472, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 27066.208984375, "min": 27066.208984375, "max": 44938.89453125, "count": 3 }, "Pyramids.Step.mean": { "value": 89961.0, "min": 29952.0, "max": 89961.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89961.0, "min": 29952.0, "max": 89961.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09253223985433578, "min": -0.13578973710536957, "max": -0.09253223985433578, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -22.300270080566406, "min": -32.182167053222656, "max": -22.300270080566406, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.199475958943367, "min": 0.199475958943367, "max": 0.33898448944091797, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 48.073707580566406, "min": 48.073707580566406, "max": 80.33932495117188, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07189497155276138, "min": 0.06806003932545993, "max": 0.07194849411406049, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7908446870803751, "min": 0.5036394587984234, "max": 0.7908446870803751, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0012177477248836357, "min": 0.0012177477248836357, "max": 0.006861717372968955, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.013395224973719993, "min": 0.013395224973719993, "max": 0.04803202161078268, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.062171282309092e-05, "min": 7.062171282309092e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007768388410540001, "min": 0.0007768388410540001, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12354054545454547, "min": 0.12354054545454547, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3589460000000002, "min": 1.2868480000000002, "max": 1.55428, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002361700490909092, "min": 0.002361700490909092, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.02597870540000001, "min": 0.02597870540000001, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.13629108667373657, "min": 0.13629108667373657, "max": 0.5466458797454834, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.499202013015747, "min": 1.499202013015747, "max": 3.826521158218384, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 984.53125, "min": 984.53125, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31505.0, "min": 15984.0, "max": 31896.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8604313000105321, "min": -1.0000000521540642, "max": -0.8604313000105321, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.53380160033703, "min": -29.926401674747467, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8604313000105321, "min": -1.0000000521540642, "max": -0.8604313000105321, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.53380160033703, "min": -29.926401674747467, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.6182480880524963, "min": 1.6182480880524963, "max": 11.05203421600163, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 51.78393881767988, "min": 51.78393881767988, "max": 176.83254745602608, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682274464", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682274671" }, "total": 206.27008753400014, "count": 1, "self": 0.4815255750002052, "children": { "run_training.setup": { "total": 0.18821459499986304, "count": 1, "self": 0.18821459499986304 }, "TrainerController.start_learning": { "total": 205.60034736400007, "count": 1, "self": 0.14155843599451146, "children": { "TrainerController._reset_env": { "total": 4.280351689000099, "count": 1, "self": 4.280351689000099 }, "TrainerController.advance": { "total": 201.05487934600524, "count": 6288, "self": 0.1638357480042032, "children": { "env_step": { "total": 140.15368671299962, "count": 6288, "self": 128.0463472810086, "children": { "SubprocessEnvManager._take_step": { "total": 12.01207622099696, "count": 6288, "self": 0.5344480469882456, "children": { "TorchPolicy.evaluate": { "total": 11.477628174008714, "count": 6281, "self": 11.477628174008714 } } }, "workers": { "total": 0.09526321099406232, "count": 6288, "self": 0.0, "children": { "worker_root": { "total": 205.1043499409866, "count": 6288, "is_parallel": true, "self": 89.41321146598625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028012989998842386, "count": 1, "is_parallel": true, "self": 0.0009190779999244114, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018822209999598272, "count": 8, "is_parallel": true, "self": 0.0018822209999598272 } } }, "UnityEnvironment.step": { "total": 0.05221010299987938, "count": 1, "is_parallel": true, "self": 0.0005575870000029681, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005302889999256877, "count": 1, "is_parallel": true, "self": 0.0005302889999256877 }, "communicator.exchange": { "total": 0.04929830700007187, "count": 1, "is_parallel": true, "self": 0.04929830700007187 }, "steps_from_proto": { "total": 0.0018239199998788536, "count": 1, "is_parallel": true, "self": 0.00043421499981377565, "children": { "_process_rank_one_or_two_observation": { "total": 0.001389705000065078, "count": 8, "is_parallel": true, "self": 0.001389705000065078 } } } } } } }, "UnityEnvironment.step": { "total": 115.69113847500034, "count": 6287, "is_parallel": true, "self": 3.3406498739839208, "children": { "UnityEnvironment._generate_step_input": { "total": 2.556138471013128, "count": 6287, "is_parallel": true, "self": 2.556138471013128 }, "communicator.exchange": { "total": 99.62355481899317, "count": 6287, "is_parallel": true, "self": 99.62355481899317 }, "steps_from_proto": { "total": 10.170795311010124, "count": 6287, "is_parallel": true, "self": 2.23230032399465, "children": { "_process_rank_one_or_two_observation": { "total": 7.938494987015474, "count": 50296, "is_parallel": true, "self": 7.938494987015474 } } } } } } } } } } }, "trainer_advance": { "total": 60.73735688500142, "count": 6288, "self": 0.19752208400723248, "children": { "process_trajectory": { "total": 10.757370307993824, "count": 6288, "self": 10.757370307993824 }, "_update_policy": { "total": 49.78246449300036, "count": 32, "self": 31.788009819000536, "children": { "TorchPPOOptimizer.update": { "total": 17.994454673999826, "count": 2331, "self": 17.994454673999826 } } } } } } }, "trainer_threads": { "total": 1.0390001534688054e-06, "count": 1, "self": 1.0390001534688054e-06 }, "TrainerController._save_models": { "total": 0.12355685400007133, "count": 1, "self": 0.0014182580000579037, "children": { "RLTrainer._checkpoint": { "total": 0.12213859600001342, "count": 1, "self": 0.12213859600001342 } } } } } } }