{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7791247963905334, "min": 0.7560670971870422, "max": 1.4838001728057861, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 23635.529296875, "min": 22379.5859375, "max": 45012.5625, "count": 10 }, "Pyramids.Step.mean": { "value": 299903.0, "min": 29877.0, "max": 299903.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299903.0, "min": 29877.0, "max": 299903.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0642586201429367, "min": -0.13177074491977692, "max": -0.0642586201429367, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.550586700439453, "min": -31.22966766357422, "max": -15.550586700439453, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03877776488661766, "min": 0.03877776488661766, "max": 0.3745594918727875, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.3842191696167, "min": 9.3842191696167, "max": 88.77059936523438, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06953231513326322, "min": 0.06669966919980377, "max": 0.07366801302741358, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.973452411865685, "min": 0.5635750511891624, "max": 0.9959958189398583, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0024346989993405408, "min": 0.0008716442391914917, "max": 0.007043386170792958, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03408578599076757, "min": 0.011069152864609228, "max": 0.05634708936634367, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5387094871000003e-05, "min": 1.5387094871000003e-05, "max": 0.0002840508803163749, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00021541932819400003, "min": 0.00021541932819400003, "max": 0.002554222148592666, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10512900000000001, "min": 0.10512900000000001, "max": 0.19468362500000003, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4718060000000002, "min": 1.4718060000000002, "max": 2.171375666666667, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005223871000000002, "min": 0.0005223871000000002, "max": 0.0094688941375, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.0073134194000000026, "min": 0.0073134194000000026, "max": 0.0851555926, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.035294752568006516, "min": 0.035294752568006516, "max": 0.37586709856987, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4941265285015106, "min": 0.4941265285015106, "max": 3.00693678855896, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 949.9705882352941, "min": 949.9705882352941, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32299.0, "min": 16804.0, "max": 32514.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.666280053130218, "min": -0.9999742455059483, "max": -0.666280053130218, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.31980185955763, "min": -30.999201610684395, "max": -14.819200910627842, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.666280053130218, "min": -0.9999742455059483, "max": -0.666280053130218, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.31980185955763, "min": -30.999201610684395, "max": -14.819200910627842, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.3488791763117271, "min": 0.3488791763117271, "max": 8.131311249207048, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 12.210771170910448, "min": 10.075590851251036, "max": 138.2322912365198, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788182687", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788183644" }, "total": 956.2308544130001, "count": 1, "self": 0.6868053019998115, "children": { "run_training.setup": { "total": 0.03984891000027346, "count": 1, "self": 0.03984891000027346 }, "TrainerController.start_learning": { "total": 955.504200201, "count": 1, "self": 0.6684928139766271, "children": { "TrainerController._reset_env": { "total": 4.024218348999966, "count": 1, "self": 4.024218348999966 }, "TrainerController.advance": { "total": 950.5272183270231, "count": 18899, "self": 0.7343716990440043, "children": { "env_step": { "total": 621.7326429969671, "count": 18899, "self": 571.099877071018, "children": { "SubprocessEnvManager._take_step": { "total": 50.19520230399621, "count": 18899, "self": 2.1089920579861428, "children": { "TorchPolicy.evaluate": { "total": 48.08621024601007, "count": 18806, "self": 48.08621024601007 } } }, "workers": { "total": 0.4375636219529042, "count": 18899, "self": 0.0, "children": { "worker_root": { "total": 952.9102177039854, "count": 18899, "is_parallel": true, "self": 438.060527392051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004786624000189477, "count": 1, "is_parallel": true, "self": 0.0015638930008208263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032227309993686504, "count": 8, "is_parallel": true, "self": 0.0032227309993686504 } } }, "UnityEnvironment.step": { "total": 0.1570211080002082, "count": 1, "is_parallel": true, "self": 0.0007314170002246101, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005062580003141193, "count": 1, "is_parallel": true, "self": 0.0005062580003141193 }, "communicator.exchange": { "total": 0.151351634999628, "count": 1, "is_parallel": true, "self": 0.151351634999628 }, "steps_from_proto": { "total": 0.004431798000041454, "count": 1, "is_parallel": true, "self": 0.001067536999926233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033642610001152207, "count": 8, "is_parallel": true, "self": 0.0033642610001152207 } } } } } } }, "UnityEnvironment.step": { "total": 514.8496903119344, "count": 18898, "is_parallel": true, "self": 13.754718849948404, "children": { "UnityEnvironment._generate_step_input": { "total": 9.348042021980746, "count": 18898, "is_parallel": true, "self": 9.348042021980746 }, "communicator.exchange": { "total": 448.455892519034, "count": 18898, "is_parallel": true, "self": 448.455892519034 }, "steps_from_proto": { "total": 43.29103692097124, "count": 18898, "is_parallel": true, "self": 8.632290481934888, "children": { "_process_rank_one_or_two_observation": { "total": 34.65874643903635, "count": 151184, "is_parallel": true, "self": 34.65874643903635 } } } } } } } } } } }, "trainer_advance": { "total": 328.060203631012, "count": 18899, "self": 1.1840737840470865, "children": { "process_trajectory": { "total": 44.18694355996695, "count": 18899, "self": 44.18694355996695 }, "_update_policy": { "total": 282.68918628699794, "count": 124, "self": 108.70734992801135, "children": { "TorchPPOOptimizer.update": { "total": 173.98183635898658, "count": 6852, "self": 173.98183635898658 } } } } } } }, "trainer_threads": { "total": 1.1710003491316456e-06, "count": 1, "self": 1.1710003491316456e-06 }, "TrainerController._save_models": { "total": 0.2842695399999684, "count": 1, "self": 0.0015100780001375824, "children": { "RLTrainer._checkpoint": { "total": 0.2827594619998308, "count": 1, "self": 0.2827594619998308 } } } } } } }