{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4041188955307007, "min": 0.4041188955307007, "max": 1.4762344360351562, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12168.828125, "min": 12168.828125, "max": 44783.046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4729914963245392, "min": -0.11048054695129395, "max": 0.5554259419441223, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.59967041015625, "min": -26.515331268310547, "max": 154.40841674804688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07363367080688477, "min": -0.04671567678451538, "max": 0.4060595631599426, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.17562484741211, "min": -12.753379821777344, "max": 96.23611450195312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06726417474511835, "min": 0.06442403566749663, "max": 0.07285555517824537, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0089626211767753, "min": 0.4734353792183596, "max": 1.0615256964354594, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01722554877056859, "min": 0.0001868276081242064, "max": 0.01722748465960779, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2583832315585288, "min": 0.0018682760812420642, "max": 0.2583832315585288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4700575100133315e-06, "min": 7.4700575100133315e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011205086265019997, "min": 0.00011205086265019997, "max": 0.003260591913136099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248998666666667, "min": 0.10248998666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373498, "min": 1.3691136000000002, "max": 2.4005456000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258749668, "min": 0.000258749668, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038812450199999997, "min": 0.0038812450199999997, "max": 0.10870770360999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008808051235973835, "min": 0.008808051235973835, "max": 0.4030616879463196, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1321207731962204, "min": 0.1316964477300644, "max": 2.821431875228882, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.57954545454544, "min": 339.6470588235294, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31819.0, "min": 15984.0, "max": 33577.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5702249797230416, "min": -1.0000000521540642, "max": 1.6603529199081308, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.17979821562767, "min": -32.000001668930054, "max": 141.12999819219112, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5702249797230416, "min": -1.0000000521540642, "max": 1.6603529199081308, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.17979821562767, "min": -32.000001668930054, "max": 141.12999819219112, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03251961290202003, "min": 0.03251961290202003, "max": 8.365441800095141, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8617259353777627, "min": 2.7665224708034657, "max": 133.84706880152225, "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": "1748418856", "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 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748421139" }, "total": 2283.1862066949993, "count": 1, "self": 0.5257499509984882, "children": { "run_training.setup": { "total": 0.02139723500022228, "count": 1, "self": 0.02139723500022228 }, "TrainerController.start_learning": { "total": 2282.6390595090006, "count": 1, "self": 1.458739343972411, "children": { "TrainerController._reset_env": { "total": 2.516204025999741, "count": 1, "self": 2.516204025999741 }, "TrainerController.advance": { "total": 2278.5526684620277, "count": 63671, "self": 1.564051564022975, "children": { "env_step": { "total": 1565.1957531439289, "count": 63671, "self": 1405.2128530958712, "children": { "SubprocessEnvManager._take_step": { "total": 159.17605808898634, "count": 63671, "self": 4.825674952006466, "children": { "TorchPolicy.evaluate": { "total": 154.35038313697987, "count": 62565, "self": 154.35038313697987 } } }, "workers": { "total": 0.8068419590713347, "count": 63671, "self": 0.0, "children": { "worker_root": { "total": 2277.2698116790366, "count": 63671, "is_parallel": true, "self": 988.9785354160103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022351990000970545, "count": 1, "is_parallel": true, "self": 0.000756870000714116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014783289993829385, "count": 8, "is_parallel": true, "self": 0.0014783289993829385 } } }, "UnityEnvironment.step": { "total": 0.051341808999950445, "count": 1, "is_parallel": true, "self": 0.0005265919999146718, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004849209999520099, "count": 1, "is_parallel": true, "self": 0.0004849209999520099 }, "communicator.exchange": { "total": 0.04865967099976842, "count": 1, "is_parallel": true, "self": 0.04865967099976842 }, "steps_from_proto": { "total": 0.00167062500031534, "count": 1, "is_parallel": true, "self": 0.0003709760003403062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012996489999750338, "count": 8, "is_parallel": true, "self": 0.0012996489999750338 } } } } } } }, "UnityEnvironment.step": { "total": 1288.2912762630262, "count": 63670, "is_parallel": true, "self": 33.037711398869305, "children": { "UnityEnvironment._generate_step_input": { "total": 23.548564815003374, "count": 63670, "is_parallel": true, "self": 23.548564815003374 }, "communicator.exchange": { "total": 1133.4909684541185, "count": 63670, "is_parallel": true, "self": 1133.4909684541185 }, "steps_from_proto": { "total": 98.21403159503507, "count": 63670, "is_parallel": true, "self": 19.971864765979262, "children": { "_process_rank_one_or_two_observation": { "total": 78.2421668290558, "count": 509360, "is_parallel": true, "self": 78.2421668290558 } } } } } } } } } } }, "trainer_advance": { "total": 711.7928637540758, "count": 63671, "self": 2.6797905961084325, "children": { "process_trajectory": { "total": 133.23277092397893, "count": 63671, "self": 133.01009805397962, "children": { "RLTrainer._checkpoint": { "total": 0.22267286999931457, "count": 2, "self": 0.22267286999931457 } } }, "_update_policy": { "total": 575.8803022339885, "count": 437, "self": 319.1152450300797, "children": { "TorchPPOOptimizer.update": { "total": 256.7650572039088, "count": 22836, "self": 256.7650572039088 } } } } } } }, "trainer_threads": { "total": 9.370005500386469e-07, "count": 1, "self": 9.370005500386469e-07 }, "TrainerController._save_models": { "total": 0.11144674000024679, "count": 1, "self": 0.0012984120003238786, "children": { "RLTrainer._checkpoint": { "total": 0.11014832799992291, "count": 1, "self": 0.11014832799992291 } } } } } } }