{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32241544127464294, "min": 0.3154456317424774, "max": 1.3853167295455933, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9682.7802734375, "min": 9459.6884765625, "max": 42024.96875, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.53630131483078, "min": -0.10014563053846359, "max": 0.6021657586097717, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.80136108398438, "min": -24.03495216369629, "max": 170.41290283203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023118365556001663, "min": -0.04504852369427681, "max": 0.3278687298297882, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.2419586181640625, "min": -12.163101196289062, "max": 79.34423065185547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06784883607871875, "min": 0.06566781311456364, "max": 0.07377533632840176, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9498837051020624, "min": 0.5030132872027402, "max": 1.0308698762479858, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013079143888067584, "min": 0.0002819595140625763, "max": 0.015887268692472197, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1831080144329462, "min": 0.003101554654688339, "max": 0.22630593674324606, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.649197450299994e-06, "min": 7.649197450299994e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010708876430419991, "min": 0.00010708876430419991, "max": 0.0033320376893207996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254970000000001, "min": 0.10254970000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356958000000002, "min": 1.3886848, "max": 2.4853815000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002647150299999999, "min": 0.0002647150299999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037060104199999984, "min": 0.0037060104199999984, "max": 0.11107685207999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01259326096624136, "min": 0.01259326096624136, "max": 0.4843781888484955, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1763056516647339, "min": 0.1763056516647339, "max": 3.3906474113464355, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.280487804878, "min": 304.8804347826087, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30363.0, "min": 15984.0, "max": 32718.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5321170511405642, "min": -1.0000000521540642, "max": 1.6516282424006774, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.63359819352627, "min": -31.99640165269375, "max": 151.9497983008623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5321170511405642, "min": -1.0000000521540642, "max": 1.6516282424006774, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.63359819352627, "min": -31.99640165269375, "max": 151.9497983008623, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04840575382837503, "min": 0.04351499413947433, "max": 9.0876689767465, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9692718139267527, "min": 3.9692718139267527, "max": 145.402703627944, "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": "1679232880", "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": "1679235066" }, "total": 2185.986087629, "count": 1, "self": 0.48848039599988624, "children": { "run_training.setup": { "total": 0.11135860600006708, "count": 1, "self": 0.11135860600006708 }, "TrainerController.start_learning": { "total": 2185.386248627, "count": 1, "self": 1.3447467459977815, "children": { "TrainerController._reset_env": { "total": 6.415673233000007, "count": 1, "self": 6.415673233000007 }, "TrainerController.advance": { "total": 2177.533439132002, "count": 63908, "self": 1.4466596950333042, "children": { "env_step": { "total": 1562.6298051789802, "count": 63908, "self": 1455.3980869580037, "children": { "SubprocessEnvManager._take_step": { "total": 106.37870858496194, "count": 63908, "self": 4.627060455940182, "children": { "TorchPolicy.evaluate": { "total": 101.75164812902176, "count": 62548, "self": 101.75164812902176 } } }, "workers": { "total": 0.8530096360145762, "count": 63908, "self": 0.0, "children": { "worker_root": { "total": 2180.6491726049753, "count": 63908, "is_parallel": true, "self": 841.299157804995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019935509999413625, "count": 1, "is_parallel": true, "self": 0.0006536949995279429, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013398560004134197, "count": 8, "is_parallel": true, "self": 0.0013398560004134197 } } }, "UnityEnvironment.step": { "total": 0.08206498899994585, "count": 1, "is_parallel": true, "self": 0.0005529239997486002, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046368800008167455, "count": 1, "is_parallel": true, "self": 0.00046368800008167455 }, "communicator.exchange": { "total": 0.07956520200013983, "count": 1, "is_parallel": true, "self": 0.07956520200013983 }, "steps_from_proto": { "total": 0.0014831749999757449, "count": 1, "is_parallel": true, "self": 0.00031684700024925405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011663279997264908, "count": 8, "is_parallel": true, "self": 0.0011663279997264908 } } } } } } }, "UnityEnvironment.step": { "total": 1339.3500147999803, "count": 63907, "is_parallel": true, "self": 30.99801698000283, "children": { "UnityEnvironment._generate_step_input": { "total": 23.28397711196658, "count": 63907, "is_parallel": true, "self": 23.28397711196658 }, "communicator.exchange": { "total": 1194.049272658004, "count": 63907, "is_parallel": true, "self": 1194.049272658004 }, "steps_from_proto": { "total": 91.01874805000693, "count": 63907, "is_parallel": true, "self": 19.54400765875016, "children": { "_process_rank_one_or_two_observation": { "total": 71.47474039125677, "count": 511256, "is_parallel": true, "self": 71.47474039125677 } } } } } } } } } } }, "trainer_advance": { "total": 613.4569742579888, "count": 63908, "self": 2.568288959041638, "children": { "process_trajectory": { "total": 116.45193927394826, "count": 63908, "self": 116.2514353449485, "children": { "RLTrainer._checkpoint": { "total": 0.20050392899975122, "count": 2, "self": 0.20050392899975122 } } }, "_update_policy": { "total": 494.4367460249989, "count": 449, "self": 314.5994874890505, "children": { "TorchPPOOptimizer.update": { "total": 179.83725853594842, "count": 22818, "self": 179.83725853594842 } } } } } } }, "trainer_threads": { "total": 9.089999366551638e-07, "count": 1, "self": 9.089999366551638e-07 }, "TrainerController._save_models": { "total": 0.09238860699997531, "count": 1, "self": 0.0013754460001109692, "children": { "RLTrainer._checkpoint": { "total": 0.09101316099986434, "count": 1, "self": 0.09101316099986434 } } } } } } }