{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6665168404579163, "min": 0.6665168404579163, "max": 1.5946495532989502, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20091.484375, "min": 20091.484375, "max": 48375.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18970997631549835, "min": -0.10716152936220169, "max": 0.2471831738948822, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 48.94517517089844, "min": -25.825927734375, "max": 63.278892517089844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012041537091135979, "min": 0.006680199410766363, "max": 0.45380517840385437, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1067166328430176, "min": 1.6566894054412842, "max": 107.55182647705078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06943605918994374, "min": 0.06585919048631608, "max": 0.07194191388609512, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.48605241432960616, "min": 0.2788896204778683, "max": 0.562897801988069, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01099524283372808, "min": 0.0001414999053914558, "max": 0.01099524283372808, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07696669983609657, "min": 0.0009904993377401906, "max": 0.08602394675108371, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.058011756757141e-06, "min": 5.058011756757141e-06, "max": 0.00019696640151680003, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.540608229729999e-05, "min": 3.540608229729999e-05, "max": 0.0012125400937299997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.09999999999999999, "min": 0.09999999999999998, "max": 0.1, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7, "min": 0.3999999999999999, "max": 0.8, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001361949614285714, "min": 0.0001361949614285714, "max": 0.00492431168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009533647299999998, "min": 0.0009533647299999998, "max": 0.030322873000000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01803797110915184, "min": 0.01787019893527031, "max": 0.534096896648407, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12626579403877258, "min": 0.12509138882160187, "max": 2.136387586593628, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 613.4, "min": 601.3877551020408, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30670.0, "min": 15984.0, "max": 34234.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9464479768276215, "min": -1.0000000521540642, "max": 1.0311673174099045, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.32239884138107, "min": -32.000001668930054, "max": 50.52719855308533, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9464479768276215, "min": -1.0000000521540642, "max": 1.0311673174099045, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.32239884138107, "min": -32.000001668930054, "max": 50.52719855308533, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11382588352775201, "min": 0.11363009977325493, "max": 12.171295398846269, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.691294176387601, "min": 4.879276555497199, "max": 194.7407263815403, "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": "1749443559", "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_2 --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": "1749445647" }, "total": 2087.5942535270005, "count": 1, "self": 0.47591953500068485, "children": { "run_training.setup": { "total": 0.020292706999498478, "count": 1, "self": 0.020292706999498478 }, "TrainerController.start_learning": { "total": 2087.0980412850004, "count": 1, "self": 1.2929630827520668, "children": { "TrainerController._reset_env": { "total": 3.044654459999947, "count": 1, "self": 3.044654459999947 }, "TrainerController.advance": { "total": 2082.6721911832474, "count": 63274, "self": 1.338734979455694, "children": { "env_step": { "total": 1396.3939620187084, "count": 63274, "self": 1246.1081086676086, "children": { "SubprocessEnvManager._take_step": { "total": 149.5401656600543, "count": 63274, "self": 4.545523447043706, "children": { "TorchPolicy.evaluate": { "total": 144.9946422130106, "count": 62561, "self": 144.9946422130106 } } }, "workers": { "total": 0.7456876910455321, "count": 63274, "self": 0.0, "children": { "worker_root": { "total": 2082.456540916074, "count": 63274, "is_parallel": true, "self": 943.1106912942269, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002521911999792792, "count": 1, "is_parallel": true, "self": 0.0007934859995657462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017284260002270457, "count": 8, "is_parallel": true, "self": 0.0017284260002270457 } } }, "UnityEnvironment.step": { "total": 0.049979223999798705, "count": 1, "is_parallel": true, "self": 0.0005230350006968365, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004515149994404055, "count": 1, "is_parallel": true, "self": 0.0004515149994404055 }, "communicator.exchange": { "total": 0.047415748000275926, "count": 1, "is_parallel": true, "self": 0.047415748000275926 }, "steps_from_proto": { "total": 0.0015889259993855376, "count": 1, "is_parallel": true, "self": 0.00033522400008223485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012537019993033027, "count": 8, "is_parallel": true, "self": 0.0012537019993033027 } } } } } } }, "UnityEnvironment.step": { "total": 1139.3458496218473, "count": 63273, "is_parallel": true, "self": 31.04758551323812, "children": { "UnityEnvironment._generate_step_input": { "total": 22.727993597838577, "count": 63273, "is_parallel": true, "self": 22.727993597838577 }, "communicator.exchange": { "total": 993.7852744339243, "count": 63273, "is_parallel": true, "self": 993.7852744339243 }, "steps_from_proto": { "total": 91.78499607684626, "count": 63273, "is_parallel": true, "self": 17.978266948128294, "children": { "_process_rank_one_or_two_observation": { "total": 73.80672912871796, "count": 506184, "is_parallel": true, "self": 73.80672912871796 } } } } } } } } } } }, "trainer_advance": { "total": 684.9394941850833, "count": 63274, "self": 2.440142136817485, "children": { "process_trajectory": { "total": 125.25541883626374, "count": 63274, "self": 125.05289813026411, "children": { "RLTrainer._checkpoint": { "total": 0.2025207059996319, "count": 2, "self": 0.2025207059996319 } } }, "_update_policy": { "total": 557.243933212002, "count": 231, "self": 307.9904933010275, "children": { "TorchPPOOptimizer.update": { "total": 249.25343991097452, "count": 23148, "self": 249.25343991097452 } } } } } } }, "trainer_threads": { "total": 8.320002962136641e-07, "count": 1, "self": 8.320002962136641e-07 }, "TrainerController._save_models": { "total": 0.08823172700067516, "count": 1, "self": 0.0011536390011315234, "children": { "RLTrainer._checkpoint": { "total": 0.08707808799954364, "count": 1, "self": 0.08707808799954364 } } } } } } }