{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3484613001346588, "min": 0.34505295753479004, "max": 1.3996928930282593, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10414.8115234375, "min": 10358.513671875, "max": 42461.08203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29955.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29955.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5230050086975098, "min": -0.11888987571001053, "max": 0.5623978972434998, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.82638549804688, "min": -28.6524600982666, "max": 156.66464233398438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0300500076264143, "min": -0.003095264546573162, "max": 0.6129092574119568, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.263751983642578, "min": -0.8511977195739746, "max": 145.87240600585938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06793067547758774, "min": 0.06470042295820479, "max": 0.07349821394492666, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9510294566862284, "min": 0.5841224548430037, "max": 1.048497767869027, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016972815109987834, "min": 0.00037779336766323516, "max": 0.018010709256567576, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23761941153982966, "min": 0.004155727044295587, "max": 0.27016063884851366, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.600340323728567e-06, "min": 7.600340323728567e-06, "max": 0.00029530702656432493, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010640476453219994, "min": 0.00010640476453219994, "max": 0.0035073581308807003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253341428571429, "min": 0.10253341428571429, "max": 0.19843567500000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354678, "min": 1.4354678, "max": 2.5691193000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630880871428571, "min": 0.0002630880871428571, "max": 0.0098437239325, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003683233219999999, "min": 0.003683233219999999, "max": 0.11693501807000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011282311752438545, "min": 0.011134086176753044, "max": 0.6456237435340881, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15795236825942993, "min": 0.15587720274925232, "max": 5.164989948272705, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 346.32142857142856, "min": 318.74468085106383, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29091.0, "min": 16498.0, "max": 33345.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5584095105351436, "min": -0.9999375520274043, "max": 1.6386936002589287, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.90639888495207, "min": -31.998001664876938, "max": 154.0371984243393, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5584095105351436, "min": -0.9999375520274043, "max": 1.6386936002589287, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.90639888495207, "min": -31.998001664876938, "max": 154.0371984243393, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040444824521338366, "min": 0.037640641993462814, "max": 12.872380752116442, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.397365259792423, "min": 3.397365259792423, "max": 218.8304727859795, "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": "1749272971", "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 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749275146" }, "total": 2174.7338630000004, "count": 1, "self": 0.49007918300048914, "children": { "run_training.setup": { "total": 0.02273749300002237, "count": 1, "self": 0.02273749300002237 }, "TrainerController.start_learning": { "total": 2174.221046324, "count": 1, "self": 1.2757360180230535, "children": { "TrainerController._reset_env": { "total": 3.3042123660000016, "count": 1, "self": 3.3042123660000016 }, "TrainerController.advance": { "total": 2169.557118983976, "count": 63843, "self": 1.3925186570104415, "children": { "env_step": { "total": 1505.5469317169632, "count": 63843, "self": 1355.6434863580034, "children": { "SubprocessEnvManager._take_step": { "total": 149.1340477739907, "count": 63843, "self": 4.639611411986266, "children": { "TorchPolicy.evaluate": { "total": 144.49443636200442, "count": 62555, "self": 144.49443636200442 } } }, "workers": { "total": 0.7693975849691697, "count": 63843, "self": 0.0, "children": { "worker_root": { "total": 2169.442359769981, "count": 63843, "is_parallel": true, "self": 922.0602551239726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004971855000007963, "count": 1, "is_parallel": true, "self": 0.0036047199999984514, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013671350000095117, "count": 8, "is_parallel": true, "self": 0.0013671350000095117 } } }, "UnityEnvironment.step": { "total": 0.055141218000017034, "count": 1, "is_parallel": true, "self": 0.0006327190000092742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005145610000454326, "count": 1, "is_parallel": true, "self": 0.0005145610000454326 }, "communicator.exchange": { "total": 0.05040408899992599, "count": 1, "is_parallel": true, "self": 0.05040408899992599 }, "steps_from_proto": { "total": 0.003589849000036338, "count": 1, "is_parallel": true, "self": 0.002193621000174062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013962279998622762, "count": 8, "is_parallel": true, "self": 0.0013962279998622762 } } } } } } }, "UnityEnvironment.step": { "total": 1247.3821046460084, "count": 63842, "is_parallel": true, "self": 31.86792241205103, "children": { "UnityEnvironment._generate_step_input": { "total": 23.07528698398312, "count": 63842, "is_parallel": true, "self": 23.07528698398312 }, "communicator.exchange": { "total": 1098.446054080981, "count": 63842, "is_parallel": true, "self": 1098.446054080981 }, "steps_from_proto": { "total": 93.99284116899355, "count": 63842, "is_parallel": true, "self": 18.775774832046636, "children": { "_process_rank_one_or_two_observation": { "total": 75.21706633694691, "count": 510736, "is_parallel": true, "self": 75.21706633694691 } } } } } } } } } } }, "trainer_advance": { "total": 662.6176686100024, "count": 63843, "self": 2.5549564980507284, "children": { "process_trajectory": { "total": 126.71663104895254, "count": 63843, "self": 126.48241452395234, "children": { "RLTrainer._checkpoint": { "total": 0.23421652500019263, "count": 2, "self": 0.23421652500019263 } } }, "_update_policy": { "total": 533.3460810629991, "count": 453, "self": 294.3357665490472, "children": { "TorchPPOOptimizer.update": { "total": 239.01031451395193, "count": 22782, "self": 239.01031451395193 } } } } } } }, "trainer_threads": { "total": 9.350001164420974e-07, "count": 1, "self": 9.350001164420974e-07 }, "TrainerController._save_models": { "total": 0.08397802100034824, "count": 1, "self": 0.0011178610002389178, "children": { "RLTrainer._checkpoint": { "total": 0.08286016000010932, "count": 1, "self": 0.08286016000010932 } } } } } } }