{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35942062735557556, "min": 0.3515954911708832, "max": 1.3989955186843872, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10679.10546875, "min": 10514.111328125, "max": 42439.9296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29961.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29961.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48153018951416016, "min": -0.08552796393632889, "max": 0.6536166667938232, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.93927001953125, "min": -20.526710510253906, "max": 185.62713623046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018950866535305977, "min": 0.00459246477112174, "max": 0.6789603233337402, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.192537307739258, "min": 1.2353730201721191, "max": 161.59255981445312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06881369972058261, "min": 0.06457408542961016, "max": 0.07419323876697126, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0322054958087392, "min": 0.5935459101357701, "max": 1.0629670523048844, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01545152069431626, "min": 0.001212646079764528, "max": 0.017490255732251676, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2317728104147439, "min": 0.014112671656550826, "max": 0.24486358025152347, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.513257495613329e-06, "min": 7.513257495613329e-06, "max": 0.0002948533892155375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011269886243419994, "min": 0.00011269886243419994, "max": 0.0036333712888763003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250438666666667, "min": 0.10250438666666667, "max": 0.19828446249999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375658, "min": 1.4779021000000003, "max": 2.6111237, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026018822799999997, "min": 0.00026018822799999997, "max": 0.009828617803749998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039028234199999993, "min": 0.0039028234199999993, "max": 0.12113125763000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012292472645640373, "min": 0.012292472645640373, "max": 0.755624532699585, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18438708782196045, "min": 0.17792156338691711, "max": 6.04499626159668, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 373.11494252873564, "min": 281.1276595744681, "max": 990.5151515151515, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32461.0, "min": 16376.0, "max": 33283.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.488910329667316, "min": -0.9308303504279165, "max": 1.6975850945616022, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 129.5351986810565, "min": -30.717401564121246, "max": 159.5729988887906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.488910329667316, "min": -0.9308303504279165, "max": 1.6975850945616022, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 129.5351986810565, "min": -30.717401564121246, "max": 159.5729988887906, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047472099230816085, "min": 0.04102697923820976, "max": 16.747456265942137, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.130072633080999, "min": 3.7756197740964126, "max": 284.70675652101636, "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": "1720957566", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "1720959918" }, "total": 2351.6290351439998, "count": 1, "self": 0.5373872420000225, "children": { "run_training.setup": { "total": 0.050762946000077136, "count": 1, "self": 0.050762946000077136 }, "TrainerController.start_learning": { "total": 2351.040884956, "count": 1, "self": 1.6544132050371445, "children": { "TrainerController._reset_env": { "total": 2.2374863840000216, "count": 1, "self": 2.2374863840000216 }, "TrainerController.advance": { "total": 2347.0612872829633, "count": 64063, "self": 1.6963289699838242, "children": { "env_step": { "total": 1699.997304216942, "count": 64063, "self": 1552.7933969559795, "children": { "SubprocessEnvManager._take_step": { "total": 146.18590215594713, "count": 64063, "self": 5.214304289935853, "children": { "TorchPolicy.evaluate": { "total": 140.97159786601128, "count": 62561, "self": 140.97159786601128 } } }, "workers": { "total": 1.0180051050153907, "count": 64063, "self": 0.0, "children": { "worker_root": { "total": 2345.194280150963, "count": 64063, "is_parallel": true, "self": 928.5509097650106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020690149999609275, "count": 1, "is_parallel": true, "self": 0.0006410080002297036, "children": { "_process_rank_one_or_two_observation": { "total": 0.001428006999731224, "count": 8, "is_parallel": true, "self": 0.001428006999731224 } } }, "UnityEnvironment.step": { "total": 0.04820630299991535, "count": 1, "is_parallel": true, "self": 0.0006240759998945578, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004546990001017548, "count": 1, "is_parallel": true, "self": 0.0004546990001017548 }, "communicator.exchange": { "total": 0.04528044699986822, "count": 1, "is_parallel": true, "self": 0.04528044699986822 }, "steps_from_proto": { "total": 0.0018470810000508209, "count": 1, "is_parallel": true, "self": 0.0003565350002645573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014905459997862636, "count": 8, "is_parallel": true, "self": 0.0014905459997862636 } } } } } } }, "UnityEnvironment.step": { "total": 1416.6433703859525, "count": 64062, "is_parallel": true, "self": 36.07008187405381, "children": { "UnityEnvironment._generate_step_input": { "total": 24.862057893971496, "count": 64062, "is_parallel": true, "self": 24.862057893971496 }, "communicator.exchange": { "total": 1249.9409761609488, "count": 64062, "is_parallel": true, "self": 1249.9409761609488 }, "steps_from_proto": { "total": 105.77025445697836, "count": 64062, "is_parallel": true, "self": 22.659753215835508, "children": { "_process_rank_one_or_two_observation": { "total": 83.11050124114286, "count": 512496, "is_parallel": true, "self": 83.11050124114286 } } } } } } } } } } }, "trainer_advance": { "total": 645.3676540960375, "count": 64063, "self": 3.1393107670526206, "children": { "process_trajectory": { "total": 134.5591547709805, "count": 64063, "self": 134.36237168297976, "children": { "RLTrainer._checkpoint": { "total": 0.19678308800075683, "count": 2, "self": 0.19678308800075683 } } }, "_update_policy": { "total": 507.6691885580044, "count": 457, "self": 299.6890263719795, "children": { "TorchPPOOptimizer.update": { "total": 207.98016218602493, "count": 22776, "self": 207.98016218602493 } } } } } } }, "trainer_threads": { "total": 1.3779999790131114e-06, "count": 1, "self": 1.3779999790131114e-06 }, "TrainerController._save_models": { "total": 0.08769670599940582, "count": 1, "self": 0.0014211039997462649, "children": { "RLTrainer._checkpoint": { "total": 0.08627560199965956, "count": 1, "self": 0.08627560199965956 } } } } } } }