{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5152459144592285, "min": 0.49146413803100586, "max": 1.4640523195266724, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15440.8896484375, "min": 14688.8798828125, "max": 44413.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29946.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29946.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.14191195368766785, "min": -0.1094147264957428, "max": 0.17512190341949463, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 35.903724670410156, "min": -26.478363037109375, "max": 44.48096466064453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.8513132929801941, "min": -0.005625695921480656, "max": 0.8513132929801941, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 215.38226318359375, "min": -1.3951725959777832, "max": 215.38226318359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06866212612817243, "min": 0.06424578286974116, "max": 0.0729571171991165, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9612697657944141, "min": 0.5106998203938156, "max": 1.0341804382478585, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.2627964678799837, "min": 0.0004338187815207329, "max": 0.2627964678799837, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 3.6791505503197715, "min": 0.0056396441597695275, "max": 3.6791505503197715, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.720661712192861e-06, "min": 7.720661712192861e-06, "max": 0.00029523317301751427, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010808926397070005, "min": 0.00010808926397070005, "max": 0.0034908694363768996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257352142857143, "min": 0.10257352142857143, "max": 0.19841105714285714, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360293, "min": 1.3888774, "max": 2.4636231, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026709479071428577, "min": 0.00026709479071428577, "max": 0.009841264608571428, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037393270700000008, "min": 0.0037393270700000008, "max": 0.11637594769000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010506674647331238, "min": 0.010506674647331238, "max": 0.3344995677471161, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14709344506263733, "min": 0.14709344506263733, "max": 2.3414969444274902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 687.4761904761905, "min": 648.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28874.0, "min": 16617.0, "max": 33300.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6932904491467136, "min": -0.999826718121767, "max": 0.8753809219314939, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 29.11819886416197, "min": -30.283401675522327, "max": 36.76599872112274, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6932904491467136, "min": -0.999826718121767, "max": 0.8753809219314939, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 29.11819886416197, "min": -30.283401675522327, "max": 36.76599872112274, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07526472104793702, "min": 0.07526472104793702, "max": 6.352530754664365, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.161118284013355, "min": 3.161118284013355, "max": 107.9930228292942, "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": "1709202585", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709205906" }, "total": 3320.3921392230004, "count": 1, "self": 0.994900929000778, "children": { "run_training.setup": { "total": 0.08755880499984414, "count": 1, "self": 0.08755880499984414 }, "TrainerController.start_learning": { "total": 3319.309679489, "count": 1, "self": 2.569711365873445, "children": { "TrainerController._reset_env": { "total": 3.0921257630000127, "count": 1, "self": 3.0921257630000127 }, "TrainerController.advance": { "total": 3313.473889802127, "count": 63259, "self": 2.7385616871115417, "children": { "env_step": { "total": 2146.304454579931, "count": 63259, "self": 1963.25653364904, "children": { "SubprocessEnvManager._take_step": { "total": 181.46682915294264, "count": 63259, "self": 7.818663187870243, "children": { "TorchPolicy.evaluate": { "total": 173.6481659650724, "count": 62573, "self": 173.6481659650724 } } }, "workers": { "total": 1.5810917779485862, "count": 63259, "self": 0.0, "children": { "worker_root": { "total": 3312.578731987983, "count": 63259, "is_parallel": true, "self": 1540.266702114925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022543619998032227, "count": 1, "is_parallel": true, "self": 0.0006950730000880867, "children": { "_process_rank_one_or_two_observation": { "total": 0.001559288999715136, "count": 8, "is_parallel": true, "self": 0.001559288999715136 } } }, "UnityEnvironment.step": { "total": 0.06736587799991867, "count": 1, "is_parallel": true, "self": 0.0007258829998590954, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005541830000765913, "count": 1, "is_parallel": true, "self": 0.0005541830000765913 }, "communicator.exchange": { "total": 0.06404810100002578, "count": 1, "is_parallel": true, "self": 0.06404810100002578 }, "steps_from_proto": { "total": 0.0020377109999571985, "count": 1, "is_parallel": true, "self": 0.0004675890002090455, "children": { "_process_rank_one_or_two_observation": { "total": 0.001570121999748153, "count": 8, "is_parallel": true, "self": 0.001570121999748153 } } } } } } }, "UnityEnvironment.step": { "total": 1772.3120298730578, "count": 63258, "is_parallel": true, "self": 50.3594734249848, "children": { "UnityEnvironment._generate_step_input": { "total": 31.094977112030165, "count": 63258, "is_parallel": true, "self": 31.094977112030165 }, "communicator.exchange": { "total": 1556.1132832131134, "count": 63258, "is_parallel": true, "self": 1556.1132832131134 }, "steps_from_proto": { "total": 134.74429612292943, "count": 63258, "is_parallel": true, "self": 29.268641912122575, "children": { "_process_rank_one_or_two_observation": { "total": 105.47565421080685, "count": 506064, "is_parallel": true, "self": 105.47565421080685 } } } } } } } } } } }, "trainer_advance": { "total": 1164.4308735350842, "count": 63259, "self": 4.9292068380573255, "children": { "process_trajectory": { "total": 178.73626787002217, "count": 63259, "self": 178.47868783402214, "children": { "RLTrainer._checkpoint": { "total": 0.25758003600003576, "count": 2, "self": 0.25758003600003576 } } }, "_update_policy": { "total": 980.7653988270047, "count": 448, "self": 382.10437217097433, "children": { "TorchPPOOptimizer.update": { "total": 598.6610266560303, "count": 22749, "self": 598.6610266560303 } } } } } } }, "trainer_threads": { "total": 1.782999788702e-06, "count": 1, "self": 1.782999788702e-06 }, "TrainerController._save_models": { "total": 0.17395077499986655, "count": 1, "self": 0.01314784799978952, "children": { "RLTrainer._checkpoint": { "total": 0.16080292700007703, "count": 1, "self": 0.16080292700007703 } } } } } } }