{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5344411134719849, "min": 0.5077705979347229, "max": 1.5152571201324463, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15887.865234375, "min": 15265.615234375, "max": 45966.83984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40177106857299805, "min": -0.10633585602045059, "max": 0.42841634154319763, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.26402282714844, "min": -25.626941680908203, "max": 119.09974670410156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1961318701505661, "min": -0.06456505507230759, "max": 0.21784044802188873, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 51.38655090332031, "min": -16.851478576660156, "max": 52.281707763671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06734459724201278, "min": 0.06572891073440024, "max": 0.07216782623720577, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9428243613881789, "min": 0.48531011296851, "max": 1.0772933267769131, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.040791831452122965, "min": 0.00032096227745021666, "max": 0.040791831452122965, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5710856403297215, "min": 0.0025676982196017333, "max": 0.5710856403297215, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.665183159257143e-06, "min": 7.665183159257143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001073125642296, "min": 0.0001073125642296, "max": 0.0032539119153627994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255502857142858, "min": 0.10255502857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357704, "min": 1.3691136000000002, "max": 2.4846372000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002652473542857143, "min": 0.0002652473542857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037134629600000003, "min": 0.0037134629600000003, "max": 0.10849525627999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00995674915611744, "min": 0.00995674915611744, "max": 0.33786579966545105, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13939449191093445, "min": 0.13939449191093445, "max": 2.365060567855835, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 451.0923076923077, "min": 392.91358024691357, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29321.0, "min": 15984.0, "max": 33444.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3950124765979126, "min": -1.0000000521540642, "max": 1.5329851681067619, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 89.2807985022664, "min": -32.000001668930054, "max": 124.17179861664772, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3950124765979126, "min": -1.0000000521540642, "max": 1.5329851681067619, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 89.2807985022664, "min": -32.000001668930054, "max": 124.17179861664772, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04595074188432591, "min": 0.042200578046627746, "max": 6.687923964112997, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.940847480596858, "min": 2.940847480596858, "max": 107.00678342580795, "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": "1699297424", "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": "1699299808" }, "total": 2383.627472986, "count": 1, "self": 0.5266920769995522, "children": { "run_training.setup": { "total": 0.04253116199993201, "count": 1, "self": 0.04253116199993201 }, "TrainerController.start_learning": { "total": 2383.0582497470004, "count": 1, "self": 1.605543590934758, "children": { "TrainerController._reset_env": { "total": 3.7947257870000612, "count": 1, "self": 3.7947257870000612 }, "TrainerController.advance": { "total": 2377.5792388330656, "count": 63577, "self": 1.7094205041207715, "children": { "env_step": { "total": 1719.85688479795, "count": 63577, "self": 1569.7078749249029, "children": { "SubprocessEnvManager._take_step": { "total": 149.15135678403226, "count": 63577, "self": 5.193222593070232, "children": { "TorchPolicy.evaluate": { "total": 143.95813419096203, "count": 62551, "self": 143.95813419096203 } } }, "workers": { "total": 0.9976530890148751, "count": 63577, "self": 0.0, "children": { "worker_root": { "total": 2377.6518008679795, "count": 63577, "is_parallel": true, "self": 936.6422303319664, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018191399999523128, "count": 1, "is_parallel": true, "self": 0.0005852790002336405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012338609997186722, "count": 8, "is_parallel": true, "self": 0.0012338609997186722 } } }, "UnityEnvironment.step": { "total": 0.10300508699992861, "count": 1, "is_parallel": true, "self": 0.0005590380001194717, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042520099987086724, "count": 1, "is_parallel": true, "self": 0.00042520099987086724 }, "communicator.exchange": { "total": 0.10046036099993216, "count": 1, "is_parallel": true, "self": 0.10046036099993216 }, "steps_from_proto": { "total": 0.0015604870000061055, "count": 1, "is_parallel": true, "self": 0.0003209439998954622, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012395430001106433, "count": 8, "is_parallel": true, "self": 0.0012395430001106433 } } } } } } }, "UnityEnvironment.step": { "total": 1441.0095705360131, "count": 63576, "is_parallel": true, "self": 37.21391078217994, "children": { "UnityEnvironment._generate_step_input": { "total": 25.082663968901443, "count": 63576, "is_parallel": true, "self": 25.082663968901443 }, "communicator.exchange": { "total": 1275.2703111149704, "count": 63576, "is_parallel": true, "self": 1275.2703111149704 }, "steps_from_proto": { "total": 103.44268466996141, "count": 63576, "is_parallel": true, "self": 21.324029914028188, "children": { "_process_rank_one_or_two_observation": { "total": 82.11865475593322, "count": 508608, "is_parallel": true, "self": 82.11865475593322 } } } } } } } } } } }, "trainer_advance": { "total": 656.0129335309948, "count": 63577, "self": 3.135818895026887, "children": { "process_trajectory": { "total": 125.2033299679756, "count": 63577, "self": 125.03661363697574, "children": { "RLTrainer._checkpoint": { "total": 0.16671633099986138, "count": 2, "self": 0.16671633099986138 } } }, "_update_policy": { "total": 527.6737846679923, "count": 439, "self": 313.5181837800001, "children": { "TorchPPOOptimizer.update": { "total": 214.15560088799225, "count": 22839, "self": 214.15560088799225 } } } } } } }, "trainer_threads": { "total": 9.959999260900076e-07, "count": 1, "self": 9.959999260900076e-07 }, "TrainerController._save_models": { "total": 0.0787405400001262, "count": 1, "self": 0.001396270000441291, "children": { "RLTrainer._checkpoint": { "total": 0.07734426999968491, "count": 1, "self": 0.07734426999968491 } } } } } } }