{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1602819561958313, "min": 0.15240693092346191, "max": 1.4864853620529175, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4780.2490234375, "min": 4552.74072265625, "max": 45094.01953125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999989.0, "min": 29952.0, "max": 2999989.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999989.0, "min": 29952.0, "max": 2999989.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7856408953666687, "min": -0.11383164674043655, "max": 0.8823727965354919, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 230.19277954101562, "min": -27.319595336914062, "max": 272.6531982421875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02328384853899479, "min": -0.02171221934258938, "max": 0.31984320282936096, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.822167873382568, "min": -6.5570902824401855, "max": 75.80284118652344, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06822659720399721, "min": 0.06428401357561471, "max": 0.07448217778427348, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.023398958059958, "min": 0.5088444681374501, "max": 1.1137376004332384, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013510301091041033, "min": 0.0013954339032982424, "max": 0.01675599850520181, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2026545163656155, "min": 0.012531955368443235, "max": 0.2513399775780271, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4824661725444415e-06, "min": 1.4824661725444415e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2236992588166623e-05, "min": 2.2236992588166623e-05, "max": 0.0040110411629863, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049412222222222, "min": 0.10049412222222222, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074118333333333, "min": 1.3962282666666668, "max": 2.7825097666666663, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.93628099999999e-05, "min": 5.93628099999999e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008904421499999985, "min": 0.0008904421499999985, "max": 0.13370766863, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007735994178801775, "min": 0.007570724934339523, "max": 0.38261502981185913, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11603990942239761, "min": 0.10599014908075333, "max": 2.678305149078369, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 245.6949152542373, "min": 206.19310344827585, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28992.0, "min": 15984.0, "max": 32176.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7543050707396814, "min": -1.0000000521540642, "max": 1.7938068870840402, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 207.0079983472824, "min": -29.87400171905756, "max": 260.1019986271858, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7543050707396814, "min": -1.0000000521540642, "max": 1.7938068870840402, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 207.0079983472824, "min": -29.87400171905756, "max": 260.1019986271858, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019654930028590863, "min": 0.01681934346571356, "max": 7.465409238822758, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.319281743373722, "min": 2.306462078500772, "max": 119.44654782116413, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691739501", "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": "1691749324" }, "total": 9823.705438993, "count": 1, "self": 0.58846832800009, "children": { "run_training.setup": { "total": 0.04442964400004712, "count": 1, "self": 0.04442964400004712 }, "TrainerController.start_learning": { "total": 9823.072541021, "count": 1, "self": 7.114481126214741, "children": { "TrainerController._reset_env": { "total": 4.54130061800015, "count": 1, "self": 4.54130061800015 }, "TrainerController.advance": { "total": 9811.296134569784, "count": 195596, "self": 6.663228859213632, "children": { "env_step": { "total": 7393.78037560177, "count": 195596, "self": 6916.337518200564, "children": { "SubprocessEnvManager._take_step": { "total": 473.31624206532274, "count": 195596, "self": 19.520665053338234, "children": { "TorchPolicy.evaluate": { "total": 453.7955770119845, "count": 187561, "self": 453.7955770119845 } } }, "workers": { "total": 4.126615335883798, "count": 195596, "self": 0.0, "children": { "worker_root": { "total": 9799.580187520225, "count": 195596, "is_parallel": true, "self": 3387.5460901433753, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021732889999839244, "count": 1, "is_parallel": true, "self": 0.0007041619999199611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014691270000639634, "count": 8, "is_parallel": true, "self": 0.0014691270000639634 } } }, "UnityEnvironment.step": { "total": 0.05986320599981809, "count": 1, "is_parallel": true, "self": 0.0006567089997133735, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006335299999591371, "count": 1, "is_parallel": true, "self": 0.0006335299999591371 }, "communicator.exchange": { "total": 0.056194923000020935, "count": 1, "is_parallel": true, "self": 0.056194923000020935 }, "steps_from_proto": { "total": 0.002378044000124646, "count": 1, "is_parallel": true, "self": 0.0005046099995524855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018734340005721606, "count": 8, "is_parallel": true, "self": 0.0018734340005721606 } } } } } } }, "UnityEnvironment.step": { "total": 6412.03409737685, "count": 195595, "is_parallel": true, "self": 132.9917171816369, "children": { "UnityEnvironment._generate_step_input": { "total": 93.75684870807686, "count": 195595, "is_parallel": true, "self": 93.75684870807686 }, "communicator.exchange": { "total": 5736.015889595888, "count": 195595, "is_parallel": true, "self": 5736.015889595888 }, "steps_from_proto": { "total": 449.2696418912469, "count": 195595, "is_parallel": true, "self": 95.88361706189949, "children": { "_process_rank_one_or_two_observation": { "total": 353.38602482934743, "count": 1564760, "is_parallel": true, "self": 353.38602482934743 } } } } } } } } } } }, "trainer_advance": { "total": 2410.8525301088002, "count": 195596, "self": 12.15436457066744, "children": { "process_trajectory": { "total": 456.7665956351275, "count": 195596, "self": 455.998394644128, "children": { "RLTrainer._checkpoint": { "total": 0.7682009909995031, "count": 6, "self": 0.7682009909995031 } } }, "_update_policy": { "total": 1941.9315699030053, "count": 1401, "self": 1273.299296595107, "children": { "TorchPPOOptimizer.update": { "total": 668.6322733078982, "count": 68439, "self": 668.6322733078982 } } } } } } }, "trainer_threads": { "total": 1.1829997674794868e-06, "count": 1, "self": 1.1829997674794868e-06 }, "TrainerController._save_models": { "total": 0.12062352400062082, "count": 1, "self": 0.0017040340007952182, "children": { "RLTrainer._checkpoint": { "total": 0.1189194899998256, "count": 1, "self": 0.1189194899998256 } } } } } } }