{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4262155294418335, "min": 0.4262155294418335, "max": 1.434043288230896, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12772.8271484375, "min": 12772.8271484375, "max": 43503.13671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6474452614784241, "min": -0.15219177305698395, "max": 0.6474452614784241, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.87445068359375, "min": -36.06945037841797, "max": 183.87445068359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0042303865775465965, "min": -0.022027786821126938, "max": 0.4280330538749695, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2014297246932983, "min": -5.815335750579834, "max": 101.44383239746094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07129959058947861, "min": 0.06602426743024602, "max": 0.07303833177069292, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0694938588421792, "min": 0.5039252810981044, "max": 1.0694938588421792, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016100346369138506, "min": 0.0013315602457785445, "max": 0.017388587001949507, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24150519553707758, "min": 0.01720904085052581, "max": 0.2434402180272931, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.481277506273331e-06, "min": 7.481277506273331e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011221916259409996, "min": 0.00011221916259409996, "max": 0.0036338737887088, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249372666666666, "min": 0.10249372666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374059, "min": 1.3886848, "max": 2.6112912000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002591232939999999, "min": 0.0002591232939999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038868494099999987, "min": 0.0038868494099999987, "max": 0.12114799088000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012014461681246758, "min": 0.011057534255087376, "max": 0.45217448472976685, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1802169233560562, "min": 0.1548054814338684, "max": 3.1652214527130127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.44554455445547, "min": 288.7524752475247, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30648.0, "min": 15984.0, "max": 32650.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.637134632851818, "min": -1.0000000521540642, "max": 1.6950605925586488, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.3505979180336, "min": -28.680401787161827, "max": 170.83519831299782, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.637134632851818, "min": -1.0000000521540642, "max": 1.6950605925586488, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.3505979180336, "min": -28.680401787161827, "max": 170.83519831299782, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03797279768764608, "min": 0.035964165542378745, "max": 9.08896052185446, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8352525664522545, "min": 3.257287782849744, "max": 145.42336834967136, "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": "1693562474", "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": "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": "1693564992" }, "total": 2518.0631227470003, "count": 1, "self": 0.5318386990011277, "children": { "run_training.setup": { "total": 0.04947432499966453, "count": 1, "self": 0.04947432499966453 }, "TrainerController.start_learning": { "total": 2517.4818097229995, "count": 1, "self": 1.7828981708794345, "children": { "TrainerController._reset_env": { "total": 6.091356488000201, "count": 1, "self": 6.091356488000201 }, "TrainerController.advance": { "total": 2509.5015003771205, "count": 64086, "self": 1.7465962310079703, "children": { "env_step": { "total": 1791.8745828650203, "count": 64086, "self": 1658.0557056868765, "children": { "SubprocessEnvManager._take_step": { "total": 132.7487753450755, "count": 64086, "self": 5.740163315048903, "children": { "TorchPolicy.evaluate": { "total": 127.0086120300266, "count": 62547, "self": 127.0086120300266 } } }, "workers": { "total": 1.0701018330682928, "count": 64086, "self": 0.0, "children": { "worker_root": { "total": 2510.9340917350073, "count": 64086, "is_parallel": true, "self": 993.3118788091251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021634820000144828, "count": 1, "is_parallel": true, "self": 0.0006727619997946022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014907200002198806, "count": 8, "is_parallel": true, "self": 0.0014907200002198806 } } }, "UnityEnvironment.step": { "total": 0.11275742899988472, "count": 1, "is_parallel": true, "self": 0.000684224999986327, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005797399999210029, "count": 1, "is_parallel": true, "self": 0.0005797399999210029 }, "communicator.exchange": { "total": 0.10899990500001877, "count": 1, "is_parallel": true, "self": 0.10899990500001877 }, "steps_from_proto": { "total": 0.0024935589999586227, "count": 1, "is_parallel": true, "self": 0.0005789500000901171, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019146089998685056, "count": 8, "is_parallel": true, "self": 0.0019146089998685056 } } } } } } }, "UnityEnvironment.step": { "total": 1517.6222129258822, "count": 64085, "is_parallel": true, "self": 38.411274874045375, "children": { "UnityEnvironment._generate_step_input": { "total": 26.87878960199123, "count": 64085, "is_parallel": true, "self": 26.87878960199123 }, "communicator.exchange": { "total": 1327.2819982138503, "count": 64085, "is_parallel": true, "self": 1327.2819982138503 }, "steps_from_proto": { "total": 125.05015023599526, "count": 64085, "is_parallel": true, "self": 25.331114614018134, "children": { "_process_rank_one_or_two_observation": { "total": 99.71903562197713, "count": 512680, "is_parallel": true, "self": 99.71903562197713 } } } } } } } } } } }, "trainer_advance": { "total": 715.8803212810922, "count": 64086, "self": 3.3104258121056773, "children": { "process_trajectory": { "total": 129.95281155798693, "count": 64086, "self": 129.74738952098778, "children": { "RLTrainer._checkpoint": { "total": 0.20542203699915262, "count": 2, "self": 0.20542203699915262 } } }, "_update_policy": { "total": 582.6170839109996, "count": 454, "self": 379.48641491601074, "children": { "TorchPPOOptimizer.update": { "total": 203.1306689949888, "count": 22764, "self": 203.1306689949888 } } } } } } }, "trainer_threads": { "total": 1.2519994925241917e-06, "count": 1, "self": 1.2519994925241917e-06 }, "TrainerController._save_models": { "total": 0.10605343499992159, "count": 1, "self": 0.001549587000226893, "children": { "RLTrainer._checkpoint": { "total": 0.1045038479996947, "count": 1, "self": 0.1045038479996947 } } } } } } }