{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5068792700767517, "min": 0.5068792700767517, "max": 1.4242726564407349, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15198.267578125, "min": 15198.267578125, "max": 43206.734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5484990477561951, "min": -0.12224862724542618, "max": 0.5484990477561951, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.03123474121094, "min": -29.4619197845459, "max": 153.03123474121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0894196629524231, "min": -0.06227090582251549, "max": 0.537778913974762, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 24.94808578491211, "min": -17.37358283996582, "max": 127.45360565185547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06789372474720169, "min": 0.06546683811354449, "max": 0.07335847620382042, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9505121464608237, "min": 0.513509333426743, "max": 1.0369407651984752, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019398938021151394, "min": 0.0008736946234847977, "max": 0.019398938021151394, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2715851322961195, "min": 0.010484335481817573, "max": 0.2715851322961195, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4536618011928534e-06, "min": 7.4536618011928534e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010435126521669995, "min": 0.00010435126521669995, "max": 0.0036342112885962992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248452142857144, "min": 0.10248452142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347833, "min": 1.3886848, "max": 2.6114037, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582036907142856, "min": 0.0002582036907142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036148516699999983, "min": 0.0036148516699999983, "max": 0.12115922963, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013974979519844055, "min": 0.013974979519844055, "max": 0.5730299353599548, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19564971327781677, "min": 0.19564971327781677, "max": 4.011209487915039, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.3764705882353, "min": 337.42528735632186, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29952.0, "min": 15984.0, "max": 32980.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5770117479212145, "min": -1.0000000521540642, "max": 1.6165792889807415, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.04599857330322, "min": -29.183401599526405, "max": 140.64239814132452, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5770117479212145, "min": -1.0000000521540642, "max": 1.6165792889807415, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.04599857330322, "min": -29.183401599526405, "max": 140.64239814132452, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0513782316709266, "min": 0.050277656997736654, "max": 11.868546033278108, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.367149692028761, "min": 4.367149692028761, "max": 189.89673653244972, "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": "1740235760", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740237966" }, "total": 2205.843345387, "count": 1, "self": 0.47572103000038624, "children": { "run_training.setup": { "total": 0.019403168999815534, "count": 1, "self": 0.019403168999815534 }, "TrainerController.start_learning": { "total": 2205.348221188, "count": 1, "self": 1.3324631301056797, "children": { "TrainerController._reset_env": { "total": 2.122890899999902, "count": 1, "self": 2.122890899999902 }, "TrainerController.advance": { "total": 2201.805272837895, "count": 63734, "self": 1.310865644889418, "children": { "env_step": { "total": 1534.379492384073, "count": 63734, "self": 1382.57479416901, "children": { "SubprocessEnvManager._take_step": { "total": 151.03295172999492, "count": 63734, "self": 4.613005919019315, "children": { "TorchPolicy.evaluate": { "total": 146.4199458109756, "count": 62573, "self": 146.4199458109756 } } }, "workers": { "total": 0.7717464850682063, "count": 63734, "self": 0.0, "children": { "worker_root": { "total": 2200.3902346630216, "count": 63734, "is_parallel": true, "self": 929.1048737610283, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020038119998844195, "count": 1, "is_parallel": true, "self": 0.0006526329998450819, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013511790000393376, "count": 8, "is_parallel": true, "self": 0.0013511790000393376 } } }, "UnityEnvironment.step": { "total": 0.04622816799997054, "count": 1, "is_parallel": true, "self": 0.0005513619998964714, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046977700003481004, "count": 1, "is_parallel": true, "self": 0.00046977700003481004 }, "communicator.exchange": { "total": 0.04362384299997757, "count": 1, "is_parallel": true, "self": 0.04362384299997757 }, "steps_from_proto": { "total": 0.001583186000061687, "count": 1, "is_parallel": true, "self": 0.0003243779997319507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012588080003297364, "count": 8, "is_parallel": true, "self": 0.0012588080003297364 } } } } } } }, "UnityEnvironment.step": { "total": 1271.2853609019933, "count": 63733, "is_parallel": true, "self": 31.303316082004585, "children": { "UnityEnvironment._generate_step_input": { "total": 23.258138698987295, "count": 63733, "is_parallel": true, "self": 23.258138698987295 }, "communicator.exchange": { "total": 1120.2953386080212, "count": 63733, "is_parallel": true, "self": 1120.2953386080212 }, "steps_from_proto": { "total": 96.42856751298018, "count": 63733, "is_parallel": true, "self": 19.44254916807131, "children": { "_process_rank_one_or_two_observation": { "total": 76.98601834490887, "count": 509864, "is_parallel": true, "self": 76.98601834490887 } } } } } } } } } } }, "trainer_advance": { "total": 666.1149148089323, "count": 63734, "self": 2.5814839528866287, "children": { "process_trajectory": { "total": 127.13588374704796, "count": 63734, "self": 126.93237409404719, "children": { "RLTrainer._checkpoint": { "total": 0.20350965300076496, "count": 2, "self": 0.20350965300076496 } } }, "_update_policy": { "total": 536.3975471089977, "count": 456, "self": 295.539465739, "children": { "TorchPPOOptimizer.update": { "total": 240.85808136999776, "count": 22785, "self": 240.85808136999776 } } } } } } }, "trainer_threads": { "total": 1.1829997674794868e-06, "count": 1, "self": 1.1829997674794868e-06 }, "TrainerController._save_models": { "total": 0.08759313700011262, "count": 1, "self": 0.0014959399995859712, "children": { "RLTrainer._checkpoint": { "total": 0.08609719700052665, "count": 1, "self": 0.08609719700052665 } } } } } } }