{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7419354319572449, "min": 0.7226818799972534, "max": 1.481776475906372, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22079.998046875, "min": 21495.44921875, "max": 44951.171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.23665128648281097, "min": -0.10270895063877106, "max": 0.2971068322658539, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.529335021972656, "min": -24.752857208251953, "max": 76.35645294189453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4991277754306793, "min": -0.01565450243651867, "max": 0.7946254014968872, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 129.77322387695312, "min": -3.9605891704559326, "max": 200.24560546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06865658839177782, "min": 0.06429912908400846, "max": 0.07370680599082323, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9611922374848896, "min": 0.5047541244414464, "max": 1.1056020898623484, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.036569609568687156, "min": 0.00020693812340281836, "max": 0.08745890562117675, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5119745339616202, "min": 0.002897133727639457, "max": 1.2244246786964745, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.325583272457141e-06, "min": 7.325583272457141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010255816581439997, "min": 0.00010255816581439997, "max": 0.0033752686749104997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244182857142858, "min": 0.10244182857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341856000000002, "min": 1.3691136000000002, "max": 2.4844201999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002539386742857142, "min": 0.0002539386742857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035551414399999995, "min": 0.0035551414399999995, "max": 0.11252644105, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006880039814859629, "min": 0.006880039814859629, "max": 0.3733757436275482, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09632055461406708, "min": 0.09632055461406708, "max": 2.6136302947998047, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 585.8181818181819, "min": 567.7636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32220.0, "min": 15984.0, "max": 32915.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9413526938720183, "min": -1.0000000521540642, "max": 1.151952688260512, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 51.774398162961006, "min": -32.000001668930054, "max": 63.357397854328156, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9413526938720183, "min": -1.0000000521540642, "max": 1.151952688260512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 51.774398162961006, "min": -32.000001668930054, "max": 63.357397854328156, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04281714616756124, "min": 0.04281714616756124, "max": 7.293240931816399, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3549430392158683, "min": 2.2029625945724547, "max": 116.69185490906239, "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": "1754046452", "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 --force", "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": "1754049614" }, "total": 3161.4506649249997, "count": 1, "self": 0.6034748809997836, "children": { "run_training.setup": { "total": 0.058102264999888575, "count": 1, "self": 0.058102264999888575 }, "TrainerController.start_learning": { "total": 3160.789087779, "count": 1, "self": 2.2146718348767536, "children": { "TrainerController._reset_env": { "total": 5.001040826000008, "count": 1, "self": 5.001040826000008 }, "TrainerController.advance": { "total": 3153.4981764891236, "count": 63411, "self": 2.384454623095735, "children": { "env_step": { "total": 2048.3191027660414, "count": 63411, "self": 1883.1731818869685, "children": { "SubprocessEnvManager._take_step": { "total": 163.78701751600192, "count": 63411, "self": 7.200856767046389, "children": { "TorchPolicy.evaluate": { "total": 156.58616074895554, "count": 62562, "self": 156.58616074895554 } } }, "workers": { "total": 1.3589033630710219, "count": 63411, "self": 0.0, "children": { "worker_root": { "total": 3151.2277889969905, "count": 63411, "is_parallel": true, "self": 1451.8831296819887, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008056117000023733, "count": 1, "is_parallel": true, "self": 0.006074593999983335, "children": { "_process_rank_one_or_two_observation": { "total": 0.001981523000040397, "count": 8, "is_parallel": true, "self": 0.001981523000040397 } } }, "UnityEnvironment.step": { "total": 0.0681262749999405, "count": 1, "is_parallel": true, "self": 0.0006891190000715142, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005253419999462494, "count": 1, "is_parallel": true, "self": 0.0005253419999462494 }, "communicator.exchange": { "total": 0.06488417099990329, "count": 1, "is_parallel": true, "self": 0.06488417099990329 }, "steps_from_proto": { "total": 0.0020276430000194523, "count": 1, "is_parallel": true, "self": 0.000478763000046456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015488799999729963, "count": 8, "is_parallel": true, "self": 0.0015488799999729963 } } } } } } }, "UnityEnvironment.step": { "total": 1699.3446593150018, "count": 63410, "is_parallel": true, "self": 46.58858229977909, "children": { "UnityEnvironment._generate_step_input": { "total": 30.50376603004611, "count": 63410, "is_parallel": true, "self": 30.50376603004611 }, "communicator.exchange": { "total": 1493.5560665371186, "count": 63410, "is_parallel": true, "self": 1493.5560665371186 }, "steps_from_proto": { "total": 128.696244448058, "count": 63410, "is_parallel": true, "self": 28.181755965085813, "children": { "_process_rank_one_or_two_observation": { "total": 100.51448848297218, "count": 507280, "is_parallel": true, "self": 100.51448848297218 } } } } } } } } } } }, "trainer_advance": { "total": 1102.7946190999867, "count": 63411, "self": 4.384535344978076, "children": { "process_trajectory": { "total": 164.1728571670044, "count": 63411, "self": 163.86035384100455, "children": { "RLTrainer._checkpoint": { "total": 0.31250332599984176, "count": 2, "self": 0.31250332599984176 } } }, "_update_policy": { "total": 934.2372265880042, "count": 440, "self": 366.0226510610239, "children": { "TorchPPOOptimizer.update": { "total": 568.2145755269803, "count": 22815, "self": 568.2145755269803 } } } } } } }, "trainer_threads": { "total": 1.0080002539325505e-06, "count": 1, "self": 1.0080002539325505e-06 }, "TrainerController._save_models": { "total": 0.07519762099946092, "count": 1, "self": 0.002137240999218193, "children": { "RLTrainer._checkpoint": { "total": 0.07306038000024273, "count": 1, "self": 0.07306038000024273 } } } } } } }