{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47975611686706543, "min": 0.47378814220428467, "max": 1.4938429594039917, "count": 25 }, "Pyramids.Policy.Entropy.sum": { "value": 14285.2177734375, "min": 14285.2177734375, "max": 45317.21875, "count": 25 }, "Pyramids.Step.mean": { "value": 749936.0, "min": 29952.0, "max": 749936.0, "count": 25 }, "Pyramids.Step.sum": { "value": 749936.0, "min": 29952.0, "max": 749936.0, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38357290625572205, "min": -0.10590120404958725, "max": 0.38357290625572205, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.87967681884766, "min": -25.52219009399414, "max": 100.87967681884766, "count": 25 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011338451877236366, "min": -0.0011351864086464047, "max": 0.2718478739261627, "count": 25 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9820127487182617, "min": -0.29401329159736633, "max": 65.24349212646484, "count": 25 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07152136664410048, "min": 0.06516212627098632, "max": 0.07262631975140214, "count": 25 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0012991330174068, "min": 0.4860786395358194, "max": 1.0893947962710322, "count": 25 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012243100583180509, "min": 0.00022409729225619316, "max": 0.012243100583180509, "count": 25 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17140340816452712, "min": 0.002913264799330511, "max": 0.17140340816452712, "count": 25 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00022647862450713333, "min": 0.00022647862450713333, "max": 0.00029838354339596195, "count": 25 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0031707007430998666, "min": 0.0020691136102954665, "max": 0.0038423156192281672, "count": 25 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17549286666666666, "min": 0.17549286666666666, "max": 0.19946118095238097, "count": 25 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4569001333333333, "min": 1.3897045333333333, "max": 2.737640933333333, "count": 25 }, "Pyramids.Policy.Beta.mean": { "value": 0.0075517373799999996, "min": 0.0075517373799999996, "max": 0.009946171977142856, "count": 25 }, "Pyramids.Policy.Beta.sum": { "value": 0.10572432332, "min": 0.06897148288, "max": 0.12808910615, "count": 25 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009924585931003094, "min": 0.00943769607692957, "max": 0.4469583034515381, "count": 25 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13894420862197876, "min": 0.13212774693965912, "max": 3.1287081241607666, "count": 25 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 487.34375, "min": 487.34375, "max": 999.0, "count": 25 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31190.0, "min": 15984.0, "max": 32420.0, "count": 25 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2625781008973718, "min": -1.0000000521540642, "max": 1.2625781008973718, "count": 25 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.8049984574318, "min": -32.000001668930054, "max": 80.8049984574318, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2625781008973718, "min": -1.0000000521540642, "max": 1.2625781008973718, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.8049984574318, "min": -32.000001668930054, "max": 80.8049984574318, "count": 25 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04957609160805987, "min": 0.04957609160805987, "max": 9.750550173223019, "count": 25 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1728698629158316, "min": 2.9829490921110846, "max": 156.0088027715683, "count": 25 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790669639", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/mlenv/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790671950" }, "total": 2310.9696667769995, "count": 1, "self": 0.5757595639997817, "children": { "run_training.setup": { "total": 0.03324937500019587, "count": 1, "self": 0.03324937500019587 }, "TrainerController.start_learning": { "total": 2310.3606578379995, "count": 1, "self": 1.7829664298506032, "children": { "TrainerController._reset_env": { "total": 2.970980673000213, "count": 1, "self": 2.970980673000213 }, "TrainerController.advance": { "total": 2305.4897473851483, "count": 47527, "self": 1.7088723162014503, "children": { "env_step": { "total": 1563.111016522953, "count": 47527, "self": 1448.492449329016, "children": { "SubprocessEnvManager._take_step": { "total": 113.57315466597538, "count": 47527, "self": 4.949414832960429, "children": { "TorchPolicy.evaluate": { "total": 108.62373983301495, "count": 46971, "self": 108.62373983301495 } } }, "workers": { "total": 1.0454125279616164, "count": 47526, "self": 0.0, "children": { "worker_root": { "total": 2304.5090746519627, "count": 47526, "is_parallel": true, "self": 990.32590354496, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003891142000156833, "count": 1, "is_parallel": true, "self": 0.0014050899999347166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024860520002221165, "count": 8, "is_parallel": true, "self": 0.0024860520002221165 } } }, "UnityEnvironment.step": { "total": 0.0629704920002041, "count": 1, "is_parallel": true, "self": 0.0006014569999024388, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005027719998906832, "count": 1, "is_parallel": true, "self": 0.0005027719998906832 }, "communicator.exchange": { "total": 0.059500355000182026, "count": 1, "is_parallel": true, "self": 0.059500355000182026 }, "steps_from_proto": { "total": 0.0023659080002289556, "count": 1, "is_parallel": true, "self": 0.0006742279997524747, "children": { "_process_rank_one_or_two_observation": { "total": 0.001691680000476481, "count": 8, "is_parallel": true, "self": 0.001691680000476481 } } } } } } }, "UnityEnvironment.step": { "total": 1314.1831711070026, "count": 47525, "is_parallel": true, "self": 33.45428375105121, "children": { "UnityEnvironment._generate_step_input": { "total": 23.568170635007846, "count": 47525, "is_parallel": true, "self": 23.568170635007846 }, "communicator.exchange": { "total": 1148.684951409945, "count": 47525, "is_parallel": true, "self": 1148.684951409945 }, "steps_from_proto": { "total": 108.47576531099867, "count": 47525, "is_parallel": true, "self": 23.181684487024086, "children": { "_process_rank_one_or_two_observation": { "total": 85.29408082397458, "count": 380200, "is_parallel": true, "self": 85.29408082397458 } } } } } } } } } } }, "trainer_advance": { "total": 740.669858545994, "count": 47526, "self": 2.9974720300579065, "children": { "process_trajectory": { "total": 108.71416873492126, "count": 47526, "self": 108.59705453392144, "children": { "RLTrainer._checkpoint": { "total": 0.11711420099982206, "count": 1, "self": 0.11711420099982206 } } }, "_update_policy": { "total": 628.9582177810148, "count": 321, "self": 255.83598419901955, "children": { "TorchPPOOptimizer.update": { "total": 373.12223358199526, "count": 17139, "self": 373.12223358199526 } } } } } } }, "trainer_threads": { "total": 2.0170000425423495e-06, "count": 1, "self": 2.0170000425423495e-06 }, "TrainerController._save_models": { "total": 0.11696133300029032, "count": 1, "self": 0.0018681210003705928, "children": { "RLTrainer._checkpoint": { "total": 0.11509321199991973, "count": 1, "self": 0.11509321199991973 } } } } } } }