{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19576652348041534, "min": 0.19576652348041534, "max": 1.3762929439544678, "count": 67 }, "Pyramids.Policy.Entropy.sum": { "value": 5863.59912109375, "min": 5863.59912109375, "max": 41751.22265625, "count": 67 }, "Pyramids.Step.mean": { "value": 2009921.0, "min": 29952.0, "max": 2009921.0, "count": 67 }, "Pyramids.Step.sum": { "value": 2009921.0, "min": 29952.0, "max": 2009921.0, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7635822892189026, "min": -0.10142569988965988, "max": 0.8740941882133484, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 226.02035522460938, "min": -24.443593978881836, "max": 269.22100830078125, "count": 67 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00020319162285886705, "min": -0.014822336845099926, "max": 0.3223037123680115, "count": 67 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.06014472246170044, "min": -3.8007009029388428, "max": 76.38597869873047, "count": 67 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07168049047911718, "min": 0.06448051858983911, "max": 0.07329414158156898, "count": 67 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0035268667076405, "min": 0.4657464049438392, "max": 1.0671968523985886, "count": 67 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0144736667848303, "min": 0.00020432826634766952, "max": 0.016485790514717522, "count": 67 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2026313349876242, "min": 0.002860595728867373, "max": 0.23768032378090231, "count": 67 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00010058057361602142, "min": 0.00010058057361602142, "max": 0.00029838354339596195, "count": 67 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0014081280306243, "min": 0.0014081280306243, "max": 0.003969058676980467, "count": 67 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13352683571428575, "min": 0.13352683571428575, "max": 0.19946118095238097, "count": 67 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8693757000000004, "min": 1.3962282666666668, "max": 2.7974504666666666, "count": 67 }, "Pyramids.Policy.Beta.mean": { "value": 0.0033593308878571426, "min": 0.0033593308878571426, "max": 0.009946171977142856, "count": 67 }, "Pyramids.Policy.Beta.sum": { "value": 0.04703063243, "min": 0.04703063243, "max": 0.13230965137999998, "count": 67 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005812970455735922, "min": 0.005675469990819693, "max": 0.3611549735069275, "count": 67 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08138158917427063, "min": 0.07945658266544342, "max": 2.5280847549438477, "count": 67 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 247.3015873015873, "min": 209.71851851851852, "max": 999.0, "count": 67 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31160.0, "min": 15984.0, "max": 33724.0, "count": 67 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.720939676203425, "min": -1.0000000521540642, "max": 1.7902814698440057, "count": 67 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 216.83839920163155, "min": -31.994401663541794, "max": 241.68799842894077, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.720939676203425, "min": -1.0000000521540642, "max": 1.7902814698440057, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 216.83839920163155, "min": -31.994401663541794, "max": 241.68799842894077, "count": 67 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01490354019407523, "min": 0.01262458516813004, "max": 7.748989377170801, "count": 67 }, "Pyramids.Policy.RndReward.sum": { "value": 1.877846064453479, "min": 1.7043189976975555, "max": 123.98383003473282, "count": 67 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1768435044", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1768439771" }, "total": 4727.646985857, "count": 1, "self": 0.35788284200043563, "children": { "run_training.setup": { "total": 0.022306855999886466, "count": 1, "self": 0.022306855999886466 }, "TrainerController.start_learning": { "total": 4727.266796159, "count": 1, "self": 2.7444940399509505, "children": { "TrainerController._reset_env": { "total": 1.9883091840001725, "count": 1, "self": 1.9883091840001725 }, "TrainerController.advance": { "total": 4722.4125025900485, "count": 131734, "self": 2.8749205599642664, "children": { "env_step": { "total": 3384.2103365988573, "count": 131734, "self": 3083.9570233758604, "children": { "SubprocessEnvManager._take_step": { "total": 298.60663487898887, "count": 131734, "self": 9.142868439113954, "children": { "TorchPolicy.evaluate": { "total": 289.4637664398749, "count": 127353, "self": 289.4637664398749 } } }, "workers": { "total": 1.6466783440080235, "count": 131733, "self": 0.0, "children": { "worker_root": { "total": 4713.683850697824, "count": 131733, "is_parallel": true, "self": 1864.9843758638012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018034349998288235, "count": 1, "is_parallel": true, "self": 0.0005689659999461583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012344689998826652, "count": 8, "is_parallel": true, "self": 0.0012344689998826652 } } }, "UnityEnvironment.step": { "total": 0.062337337999906595, "count": 1, "is_parallel": true, "self": 0.0005637019999085169, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000607341999966593, "count": 1, "is_parallel": true, "self": 0.000607341999966593 }, "communicator.exchange": { "total": 0.059557479999966745, "count": 1, "is_parallel": true, "self": 0.059557479999966745 }, "steps_from_proto": { "total": 0.00160881400006474, "count": 1, "is_parallel": true, "self": 0.00038383199967029213, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012249820003944478, "count": 8, "is_parallel": true, "self": 0.0012249820003944478 } } } } } } }, "UnityEnvironment.step": { "total": 2848.6994748340226, "count": 131732, "is_parallel": true, "self": 67.39903508427824, "children": { "UnityEnvironment._generate_step_input": { "total": 47.01774450500261, "count": 131732, "is_parallel": true, "self": 47.01774450500261 }, "communicator.exchange": { "total": 2519.1331239107885, "count": 131732, "is_parallel": true, "self": 2519.1331239107885 }, "steps_from_proto": { "total": 215.14957133395342, "count": 131732, "is_parallel": true, "self": 45.24500844289696, "children": { "_process_rank_one_or_two_observation": { "total": 169.90456289105646, "count": 1053856, "is_parallel": true, "self": 169.90456289105646 } } } } } } } } } } }, "trainer_advance": { "total": 1335.327245431227, "count": 131733, "self": 5.638088645160224, "children": { "process_trajectory": { "total": 256.3751150200603, "count": 131733, "self": 255.98472507506062, "children": { "RLTrainer._checkpoint": { "total": 0.39038994499969704, "count": 4, "self": 0.39038994499969704 } } }, "_update_policy": { "total": 1073.3140417660065, "count": 940, "self": 596.4364908469868, "children": { "TorchPPOOptimizer.update": { "total": 476.87755091901977, "count": 46437, "self": 476.87755091901977 } } } } } } }, "trainer_threads": { "total": 1.1100000847363845e-06, "count": 1, "self": 1.1100000847363845e-06 }, "TrainerController._save_models": { "total": 0.12148923499989905, "count": 1, "self": 0.0012458080000214977, "children": { "RLTrainer._checkpoint": { "total": 0.12024342699987756, "count": 1, "self": 0.12024342699987756 } } } } } } }