{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5977962613105774, "min": 0.5862976908683777, "max": 1.416605830192566, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18010.40625, "min": 17531.76171875, "max": 42974.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34043264389038086, "min": -0.13172020018100739, "max": 0.4134828448295593, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 89.87422180175781, "min": -31.74456787109375, "max": 110.39991760253906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0038713207468390465, "min": 0.0008986841421574354, "max": 0.2909627854824066, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0220286846160889, "min": 0.23994866013526917, "max": 69.83106994628906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06549806075608579, "min": 0.06301421183617968, "max": 0.07418813967556588, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9169728505852011, "min": 0.4776824788888247, "max": 1.0466907882455774, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014647448939892156, "min": 0.0002405000541464402, "max": 0.015389873248997637, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20506428515849018, "min": 0.002645500595610842, "max": 0.2154582254859669, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.466668939714288e-06, "min": 7.466668939714288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010453336515600003, "min": 0.00010453336515600003, "max": 0.0032544977151675, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248885714285715, "min": 0.10248885714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434844, "min": 1.3691136000000002, "max": 2.4845121000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586368285714286, "min": 0.0002586368285714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003620915600000001, "min": 0.003620915600000001, "max": 0.10850476675000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007909196428954601, "min": 0.007909196428954601, "max": 0.42222651839256287, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11072874814271927, "min": 0.11072874814271927, "max": 2.9555857181549072, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 501.46031746031747, "min": 407.27941176470586, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31592.0, "min": 15984.0, "max": 32509.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.212726956440343, "min": -1.0000000521540642, "max": 1.4750382081769846, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.4017982557416, "min": -32.000001668930054, "max": 100.30259815603495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.212726956440343, "min": -1.0000000521540642, "max": 1.4750382081769846, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.4017982557416, "min": -32.000001668930054, "max": 100.30259815603495, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04205093868049083, "min": 0.035840656671900756, "max": 8.541630499996245, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6492091368709225, "min": 2.4371646536892513, "max": 136.66608799993992, "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": "1704587805", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704589910" }, "total": 2105.036206628, "count": 1, "self": 0.5333700729997872, "children": { "run_training.setup": { "total": 0.047155495999959385, "count": 1, "self": 0.047155495999959385 }, "TrainerController.start_learning": { "total": 2104.455681059, "count": 1, "self": 1.3880524460596462, "children": { "TrainerController._reset_env": { "total": 2.081135816000142, "count": 1, "self": 2.081135816000142 }, "TrainerController.advance": { "total": 2100.9020634449403, "count": 63451, "self": 1.4138326569377568, "children": { "env_step": { "total": 1465.7364749330056, "count": 63451, "self": 1333.9234031020103, "children": { "SubprocessEnvManager._take_step": { "total": 130.97156996499075, "count": 63451, "self": 4.634634307032002, "children": { "TorchPolicy.evaluate": { "total": 126.33693565795875, "count": 62558, "self": 126.33693565795875 } } }, "workers": { "total": 0.8415018660045916, "count": 63451, "self": 0.0, "children": { "worker_root": { "total": 2099.399719635045, "count": 63451, "is_parallel": true, "self": 882.2823544080325, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002250645000003715, "count": 1, "is_parallel": true, "self": 0.000555407000319974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016952379996837408, "count": 8, "is_parallel": true, "self": 0.0016952379996837408 } } }, "UnityEnvironment.step": { "total": 0.04796820999990814, "count": 1, "is_parallel": true, "self": 0.0005864639999799692, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045295499990061217, "count": 1, "is_parallel": true, "self": 0.00045295499990061217 }, "communicator.exchange": { "total": 0.045340199000065695, "count": 1, "is_parallel": true, "self": 0.045340199000065695 }, "steps_from_proto": { "total": 0.0015885919999618636, "count": 1, "is_parallel": true, "self": 0.00033934499970200704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012492470002598566, "count": 8, "is_parallel": true, "self": 0.0012492470002598566 } } } } } } }, "UnityEnvironment.step": { "total": 1217.1173652270127, "count": 63450, "is_parallel": true, "self": 34.65164100006382, "children": { "UnityEnvironment._generate_step_input": { "total": 24.087522035997154, "count": 63450, "is_parallel": true, "self": 24.087522035997154 }, "communicator.exchange": { "total": 1061.0659229460098, "count": 63450, "is_parallel": true, "self": 1061.0659229460098 }, "steps_from_proto": { "total": 97.31227924494192, "count": 63450, "is_parallel": true, "self": 19.579524025960154, "children": { "_process_rank_one_or_two_observation": { "total": 77.73275521898177, "count": 507600, "is_parallel": true, "self": 77.73275521898177 } } } } } } } } } } }, "trainer_advance": { "total": 633.7517558549966, "count": 63451, "self": 2.6870708489757362, "children": { "process_trajectory": { "total": 124.07027074402231, "count": 63451, "self": 123.83912651402215, "children": { "RLTrainer._checkpoint": { "total": 0.2311442300001545, "count": 2, "self": 0.2311442300001545 } } }, "_update_policy": { "total": 506.9944142619986, "count": 444, "self": 300.1419264229603, "children": { "TorchPPOOptimizer.update": { "total": 206.8524878390383, "count": 22851, "self": 206.8524878390383 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.08442846099978851, "count": 1, "self": 0.001474282999879506, "children": { "RLTrainer._checkpoint": { "total": 0.082954177999909, "count": 1, "self": 0.082954177999909 } } } } } } }