{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33461979031562805, "min": 0.33461979031562805, "max": 1.518917202949524, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 9894.0380859375, "min": 9894.0380859375, "max": 46077.87109375, "count": 40 }, "Pyramids.Step.mean": { "value": 1199978.0, "min": 29952.0, "max": 1199978.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199978.0, "min": 29952.0, "max": 1199978.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5012540817260742, "min": -0.1040528193116188, "max": 0.6748889684677124, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.34361267089844, "min": -25.07672882080078, "max": 193.01824951171875, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030859213322401047, "min": -0.000852369936183095, "max": 0.200784832239151, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.455424308776855, "min": -0.24207305908203125, "max": 47.58600616455078, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06878518397659245, "min": 0.06597166821797634, "max": 0.07238813389880207, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9629925756722942, "min": 0.49149857970844785, "max": 1.0582949164390276, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016041594602403862, "min": 0.0008432353687803546, "max": 0.017133062102043406, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22458232443365406, "min": 0.007240542801143639, "max": 0.2457294524720055, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.503003510452382e-06, "min": 2.503003510452382e-06, "max": 0.0001973059061089524, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.5042049146333346e-05, "min": 3.5042049146333346e-05, "max": 0.0024154051922975, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10125145238095236, "min": 0.10125145238095236, "max": 0.1986529523809524, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.417520333333333, "min": 1.3742613333333336, "max": 2.6077025000000003, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001350200928571429, "min": 0.0001350200928571429, "max": 0.009865429942857143, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.0018902813000000005, "min": 0.0018902813000000005, "max": 0.12078947975000001, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006767899729311466, "min": 0.006767899729311466, "max": 0.249151811003685, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09475059807300568, "min": 0.09475059807300568, "max": 1.7440626621246338, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.64444444444445, "min": 269.3611111111111, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30298.0, "min": 15984.0, "max": 33194.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5522199829419454, "min": -1.0000000521540642, "max": 1.7102728824470645, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.69979846477509, "min": -32.000001668930054, "max": 182.9991984218359, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5522199829419454, "min": -1.0000000521540642, "max": 1.7102728824470645, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.69979846477509, "min": -32.000001668930054, "max": 182.9991984218359, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02393461782226546, "min": 0.020884671072648603, "max": 5.551887123845518, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1541156040038913, "min": 2.1541156040038913, "max": 88.83019398152828, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732039136", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=PyramidsTraining4 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732041665" }, "total": 2528.933456775001, "count": 1, "self": 0.37308582800142176, "children": { "run_training.setup": { "total": 0.061596472000019276, "count": 1, "self": 0.061596472000019276 }, "TrainerController.start_learning": { "total": 2528.4987744749997, "count": 1, "self": 2.1152514959885593, "children": { "TrainerController._reset_env": { "total": 2.2439712780014816, "count": 1, "self": 2.2439712780014816 }, "TrainerController.advance": { "total": 2524.05415153801, "count": 76847, "self": 2.080524085149591, "children": { "env_step": { "total": 1488.2804887087423, "count": 76847, "self": 1275.2958040298818, "children": { "SubprocessEnvManager._take_step": { "total": 211.6855497588822, "count": 76847, "self": 6.654079869907946, "children": { "TorchPolicy.evaluate": { "total": 205.03146988897424, "count": 75041, "self": 205.03146988897424 } } }, "workers": { "total": 1.2991349199783144, "count": 76847, "self": 0.0, "children": { "worker_root": { "total": 2525.1355605422414, "count": 76847, "is_parallel": true, "self": 1390.042444648272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023606550003023585, "count": 1, "is_parallel": true, "self": 0.0007128860015654936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016477689987368649, "count": 8, "is_parallel": true, "self": 0.0016477689987368649 } } }, "UnityEnvironment.step": { "total": 0.037620305998643744, "count": 1, "is_parallel": true, "self": 0.0004683819970523473, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003521880007610889, "count": 1, "is_parallel": true, "self": 0.0003521880007610889 }, "communicator.exchange": { "total": 0.0356604820008215, "count": 1, "is_parallel": true, "self": 0.0356604820008215 }, "steps_from_proto": { "total": 0.0011392540000088047, "count": 1, "is_parallel": true, "self": 0.00027736000083677936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008618939991720254, "count": 8, "is_parallel": true, "self": 0.0008618939991720254 } } } } } } }, "UnityEnvironment.step": { "total": 1135.0931158939693, "count": 76846, "is_parallel": true, "self": 32.71002553965809, "children": { "UnityEnvironment._generate_step_input": { "total": 19.0885076161303, "count": 76846, "is_parallel": true, "self": 19.0885076161303 }, "communicator.exchange": { "total": 997.9250851240158, "count": 76846, "is_parallel": true, "self": 997.9250851240158 }, "steps_from_proto": { "total": 85.36949761416508, "count": 76846, "is_parallel": true, "self": 19.15990496475024, "children": { "_process_rank_one_or_two_observation": { "total": 66.20959264941484, "count": 614768, "is_parallel": true, "self": 66.20959264941484 } } } } } } } } } } }, "trainer_advance": { "total": 1033.6931387441182, "count": 76847, "self": 4.144805083304163, "children": { "process_trajectory": { "total": 156.20092695782841, "count": 76847, "self": 155.99553380882935, "children": { "RLTrainer._checkpoint": { "total": 0.20539314899906458, "count": 2, "self": 0.20539314899906458 } } }, "_update_policy": { "total": 873.3474067029856, "count": 538, "self": 471.14901020782236, "children": { "TorchPPOOptimizer.update": { "total": 402.19839649516325, "count": 36440, "self": 402.19839649516325 } } } } } } }, "trainer_threads": { "total": 1.1259999155299738e-06, "count": 1, "self": 1.1259999155299738e-06 }, "TrainerController._save_models": { "total": 0.0853990369996609, "count": 1, "self": 0.0016162949996214593, "children": { "RLTrainer._checkpoint": { "total": 0.08378274200003943, "count": 1, "self": 0.08378274200003943 } } } } } } }