{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6168356537818909, "min": 0.5069231986999512, "max": 1.4504663944244385, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18613.6328125, "min": 15256.361328125, "max": 44001.34765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29883.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29883.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04777054488658905, "min": -0.11954743415117264, "max": 0.1179172545671463, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 11.799324989318848, "min": -28.691383361816406, "max": 29.243478775024414, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008090137504041195, "min": -0.00022380726295523345, "max": 0.5107805132865906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9982640743255615, "min": -0.0555042028427124, "max": 121.05498504638672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06781363377606996, "min": 0.0642064565423388, "max": 0.07249871195032763, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9493908728649794, "min": 0.49009541976389387, "max": 1.0779635689772582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004479768561774714, "min": 0.00021172939959870432, "max": 0.01495869871068683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.062716759864846, "min": 0.0027524821947831563, "max": 0.1047108909748078, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.417918955964285e-06, "min": 7.417918955964285e-06, "max": 0.00029523587301661427, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038508653835, "min": 0.0001038508653835, "max": 0.0034925008358330993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247260714285715, "min": 0.10247260714285715, "max": 0.19841195714285714, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346165000000002, "min": 1.3888837, "max": 2.4641669, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002570134535714285, "min": 0.0002570134535714285, "max": 0.009841354518571429, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035981883499999995, "min": 0.0035981883499999995, "max": 0.11643027331000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016210218891501427, "min": 0.016210218891501427, "max": 0.5714737176895142, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22694307565689087, "min": 0.22694307565689087, "max": 4.000316143035889, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 839.6388888888889, "min": 748.9459459459459, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30227.0, "min": 16682.0, "max": 33052.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.11781670753326681, "min": -0.9998774711162813, "max": 0.2778053700521186, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -4.241401471197605, "min": -31.995601654052734, "max": 10.927198588848114, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.11781670753326681, "min": -0.9998774711162813, "max": 0.2778053700521186, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -4.241401471197605, "min": -31.995601654052734, "max": 10.927198588848114, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1404097262089231, "min": 0.13262651423999183, "max": 11.835980957045274, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.0547501435212325, "min": 4.907181026879698, "max": 201.21167626976967, "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": "1718824772", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718826825" }, "total": 2053.1497227289997, "count": 1, "self": 0.477499865999107, "children": { "run_training.setup": { "total": 0.05318625300014901, "count": 1, "self": 0.05318625300014901 }, "TrainerController.start_learning": { "total": 2052.6190366100004, "count": 1, "self": 1.219839205027256, "children": { "TrainerController._reset_env": { "total": 2.320297048000157, "count": 1, "self": 2.320297048000157 }, "TrainerController.advance": { "total": 2048.9908704389723, "count": 63180, "self": 1.2640475537982638, "children": { "env_step": { "total": 1421.9403746781159, "count": 63180, "self": 1296.1371872681325, "children": { "SubprocessEnvManager._take_step": { "total": 125.05401297096387, "count": 63180, "self": 4.456992514953072, "children": { "TorchPolicy.evaluate": { "total": 120.5970204560108, "count": 62571, "self": 120.5970204560108 } } }, "workers": { "total": 0.7491744390194981, "count": 63180, "self": 0.0, "children": { "worker_root": { "total": 2048.230514083021, "count": 63180, "is_parallel": true, "self": 865.1830059800882, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019823800002995995, "count": 1, "is_parallel": true, "self": 0.0005828380008097156, "children": { "_process_rank_one_or_two_observation": { "total": 0.001399541999489884, "count": 8, "is_parallel": true, "self": 0.001399541999489884 } } }, "UnityEnvironment.step": { "total": 0.04731205400003091, "count": 1, "is_parallel": true, "self": 0.000622708000264538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004627170001185732, "count": 1, "is_parallel": true, "self": 0.0004627170001185732 }, "communicator.exchange": { "total": 0.044658384999820555, "count": 1, "is_parallel": true, "self": 0.044658384999820555 }, "steps_from_proto": { "total": 0.0015682439998272457, "count": 1, "is_parallel": true, "self": 0.0003250419995310949, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012432020002961508, "count": 8, "is_parallel": true, "self": 0.0012432020002961508 } } } } } } }, "UnityEnvironment.step": { "total": 1183.0475081029326, "count": 63179, "is_parallel": true, "self": 32.86204209493326, "children": { "UnityEnvironment._generate_step_input": { "total": 22.74568414397936, "count": 63179, "is_parallel": true, "self": 22.74568414397936 }, "communicator.exchange": { "total": 1032.8790075119905, "count": 63179, "is_parallel": true, "self": 1032.8790075119905 }, "steps_from_proto": { "total": 94.56077435202951, "count": 63179, "is_parallel": true, "self": 18.449989417590587, "children": { "_process_rank_one_or_two_observation": { "total": 76.11078493443893, "count": 505432, "is_parallel": true, "self": 76.11078493443893 } } } } } } } } } } }, "trainer_advance": { "total": 625.7864482070581, "count": 63180, "self": 2.282318427084192, "children": { "process_trajectory": { "total": 125.10564733197225, "count": 63180, "self": 124.91099192897218, "children": { "RLTrainer._checkpoint": { "total": 0.19465540300006978, "count": 2, "self": 0.19465540300006978 } } }, "_update_policy": { "total": 498.3984824480017, "count": 447, "self": 294.0368873459306, "children": { "TorchPPOOptimizer.update": { "total": 204.36159510207108, "count": 22818, "self": 204.36159510207108 } } } } } } }, "trainer_threads": { "total": 9.490004231338389e-07, "count": 1, "self": 9.490004231338389e-07 }, "TrainerController._save_models": { "total": 0.08802896900033375, "count": 1, "self": 0.0015005480008767336, "children": { "RLTrainer._checkpoint": { "total": 0.08652842099945701, "count": 1, "self": 0.08652842099945701 } } } } } } }