{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5222892165184021, "min": 0.5096771121025085, "max": 1.474210500717163, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15593.466796875, "min": 15339.2431640625, "max": 44721.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38850125670433044, "min": -0.09953605383634567, "max": 0.38850125670433044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.5643310546875, "min": -23.888652801513672, "max": 102.5643310546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030785245820879936, "min": -0.0006794921355322003, "max": 0.25463399291038513, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.127305030822754, "min": -0.17123201489448547, "max": 61.112159729003906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880414382404913, "min": 0.06375879237988785, "max": 0.07369088785262065, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9632580135366878, "min": 0.4953863620219469, "max": 1.068515623822653, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012870669599838689, "min": 0.0003697947036457584, "max": 0.012870669599838689, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18018937439774163, "min": 0.0029583576291660673, "max": 0.18018937439774163, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.349604693021432e-06, "min": 7.349604693021432e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010289446570230005, "min": 0.00010289446570230005, "max": 0.0031372709542431, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244983571428572, "min": 0.10244983571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342977000000001, "min": 1.327104, "max": 2.4014121000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000254738587857143, "min": 0.000254738587857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003566340230000002, "min": 0.003566340230000002, "max": 0.10460111430999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010372057557106018, "min": 0.010372057557106018, "max": 0.37150055170059204, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14520880579948425, "min": 0.14520880579948425, "max": 2.600503921508789, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.0625, "min": 449.0625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28740.0, "min": 15984.0, "max": 32751.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3270092050616558, "min": -1.0000000521540642, "max": 1.3270092050616558, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.25559832900763, "min": -32.000001668930054, "max": 86.25559832900763, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3270092050616558, "min": -1.0000000521540642, "max": 1.3270092050616558, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.25559832900763, "min": -32.000001668930054, "max": 86.25559832900763, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04870340741248443, "min": 0.04870340741248443, "max": 7.816980678588152, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.165721481811488, "min": 3.165721481811488, "max": 125.07169085741043, "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": "1679042181", "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": "1679044240" }, "total": 2059.184774583, "count": 1, "self": 0.48614231300007305, "children": { "run_training.setup": { "total": 0.18086104699995076, "count": 1, "self": 0.18086104699995076 }, "TrainerController.start_learning": { "total": 2058.517771223, "count": 1, "self": 1.3861559630363445, "children": { "TrainerController._reset_env": { "total": 9.302229167000007, "count": 1, "self": 9.302229167000007 }, "TrainerController.advance": { "total": 2047.7336423849636, "count": 63442, "self": 1.4527869099267718, "children": { "env_step": { "total": 1422.239555453046, "count": 63442, "self": 1312.4898113040097, "children": { "SubprocessEnvManager._take_step": { "total": 108.92178496300653, "count": 63442, "self": 4.835115680008926, "children": { "TorchPolicy.evaluate": { "total": 104.0866692829976, "count": 62557, "self": 104.0866692829976 } } }, "workers": { "total": 0.8279591860297728, "count": 63442, "self": 0.0, "children": { "worker_root": { "total": 2054.016452054995, "count": 63442, "is_parallel": true, "self": 859.2824231990023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006413771000040924, "count": 1, "is_parallel": true, "self": 0.004322608999984823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020911620000561015, "count": 8, "is_parallel": true, "self": 0.0020911620000561015 } } }, "UnityEnvironment.step": { "total": 0.05205477900000233, "count": 1, "is_parallel": true, "self": 0.0005138909999686803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004714070000204629, "count": 1, "is_parallel": true, "self": 0.0004714070000204629 }, "communicator.exchange": { "total": 0.049268851000022096, "count": 1, "is_parallel": true, "self": 0.049268851000022096 }, "steps_from_proto": { "total": 0.001800629999991088, "count": 1, "is_parallel": true, "self": 0.00037717400005021773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014234559999408702, "count": 8, "is_parallel": true, "self": 0.0014234559999408702 } } } } } } }, "UnityEnvironment.step": { "total": 1194.7340288559928, "count": 63441, "is_parallel": true, "self": 30.98936234787834, "children": { "UnityEnvironment._generate_step_input": { "total": 24.014981983033806, "count": 63441, "is_parallel": true, "self": 24.014981983033806 }, "communicator.exchange": { "total": 1044.3650701190481, "count": 63441, "is_parallel": true, "self": 1044.3650701190481 }, "steps_from_proto": { "total": 95.36461440603267, "count": 63441, "is_parallel": true, "self": 20.598968355127795, "children": { "_process_rank_one_or_two_observation": { "total": 74.76564605090488, "count": 507528, "is_parallel": true, "self": 74.76564605090488 } } } } } } } } } } }, "trainer_advance": { "total": 624.0413000219908, "count": 63442, "self": 2.511984699009645, "children": { "process_trajectory": { "total": 121.19935769897978, "count": 63442, "self": 120.99236668697966, "children": { "RLTrainer._checkpoint": { "total": 0.20699101200011683, "count": 2, "self": 0.20699101200011683 } } }, "_update_policy": { "total": 500.3299576240013, "count": 435, "self": 319.3942646189866, "children": { "TorchPPOOptimizer.update": { "total": 180.93569300501468, "count": 22860, "self": 180.93569300501468 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.0957428130000153, "count": 1, "self": 0.0014085699999668577, "children": { "RLTrainer._checkpoint": { "total": 0.09433424300004845, "count": 1, "self": 0.09433424300004845 } } } } } } }