{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8152309060096741, "min": 0.8152309060096741, "max": 1.437196135520935, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 24417.796875, "min": 24417.796875, "max": 43598.78125, "count": 10 }, "Pyramids.Step.mean": { "value": 299972.0, "min": 29952.0, "max": 299972.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299972.0, "min": 29952.0, "max": 299972.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09126388281583786, "min": -0.1276295930147171, "max": -0.02452116273343563, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.903331756591797, "min": -30.631103515625, "max": -5.909600257873535, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027795342728495598, "min": 0.027795342728495598, "max": 0.2621821165084839, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.670882225036621, "min": 6.670882225036621, "max": 62.923709869384766, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06778884891422886, "min": 0.0669969811358289, "max": 0.07124440591736071, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.949043884799204, "min": 0.498710841421525, "max": 0.972430426251901, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011166394092201866, "min": 0.0002213806678322293, "max": 0.006897937184804729, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.015632951729082613, "min": 0.0024351873461545223, "max": 0.0482855602936331, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5235594921499998e-05, "min": 1.5235594921499998e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00021329832890099997, "min": 0.00021329832890099997, "max": 0.002246072251309333, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1050785, "min": 0.1050785, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4710990000000002, "min": 1.362282666666667, "max": 2.030262666666667, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005173421500000001, "min": 0.0005173421500000001, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.007242790100000001, "min": 0.007242790100000001, "max": 0.0748941976, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02649138681590557, "min": 0.02649138681590557, "max": 0.4339198172092438, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3708794116973877, "min": 0.3708794116973877, "max": 3.0374386310577393, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 968.6060606060606, "min": 935.15625, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31964.0, "min": 15984.0, "max": 32710.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8432813030667603, "min": -1.0000000521540642, "max": -0.575014867440418, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.98500169813633, "min": -30.999201610684395, "max": -15.525401420891285, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8432813030667603, "min": -1.0000000521540642, "max": -0.575014867440418, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.98500169813633, "min": -30.999201610684395, "max": -15.525401420891285, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2738676644221414, "min": 0.2738676644221414, "max": 9.160875851288438, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 8.763765261508524, "min": 8.28425006614998, "max": 146.574013620615, "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": "1774977141", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagagents_env/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": "2.7.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1774977748" }, "total": 606.9129199470003, "count": 1, "self": 0.8038385650006603, "children": { "run_training.setup": { "total": 0.026060799999868323, "count": 1, "self": 0.026060799999868323 }, "TrainerController.start_learning": { "total": 606.0830205819998, "count": 1, "self": 0.33793641804732033, "children": { "TrainerController._reset_env": { "total": 2.4863899209999545, "count": 1, "self": 2.4863899209999545 }, "TrainerController.advance": { "total": 603.1090291959526, "count": 18912, "self": 0.35363654894854335, "children": { "env_step": { "total": 412.9961225230031, "count": 18912, "self": 368.33733089498264, "children": { "SubprocessEnvManager._take_step": { "total": 44.44815019101725, "count": 18912, "self": 1.29031875804003, "children": { "TorchPolicy.evaluate": { "total": 43.15783143297722, "count": 18821, "self": 43.15783143297722 } } }, "workers": { "total": 0.21064143700323257, "count": 18912, "self": 0.0, "children": { "worker_root": { "total": 603.6563013390055, "count": 18912, "is_parallel": true, "self": 269.08942739098984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017151470001408597, "count": 1, "is_parallel": true, "self": 0.0005347710002752137, "children": { "_process_rank_one_or_two_observation": { "total": 0.001180375999865646, "count": 8, "is_parallel": true, "self": 0.001180375999865646 } } }, "UnityEnvironment.step": { "total": 0.04720998700031487, "count": 1, "is_parallel": true, "self": 0.000542467000286706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047370199990837136, "count": 1, "is_parallel": true, "self": 0.00047370199990837136 }, "communicator.exchange": { "total": 0.04457522599977892, "count": 1, "is_parallel": true, "self": 0.04457522599977892 }, "steps_from_proto": { "total": 0.0016185920003408683, "count": 1, "is_parallel": true, "self": 0.0003913620007551799, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012272299995856883, "count": 8, "is_parallel": true, "self": 0.0012272299995856883 } } } } } } }, "UnityEnvironment.step": { "total": 334.56687394801565, "count": 18911, "is_parallel": true, "self": 9.939385102084998, "children": { "UnityEnvironment._generate_step_input": { "total": 6.759905776940286, "count": 18911, "is_parallel": true, "self": 6.759905776940286 }, "communicator.exchange": { "total": 286.37858040300216, "count": 18911, "is_parallel": true, "self": 286.37858040300216 }, "steps_from_proto": { "total": 31.48900266598821, "count": 18911, "is_parallel": true, "self": 6.601600551946831, "children": { "_process_rank_one_or_two_observation": { "total": 24.88740211404138, "count": 151288, "is_parallel": true, "self": 24.88740211404138 } } } } } } } } } } }, "trainer_advance": { "total": 189.75927012400098, "count": 18912, "self": 0.5216219530357193, "children": { "process_trajectory": { "total": 34.719873870965785, "count": 18912, "self": 34.719873870965785 }, "_update_policy": { "total": 154.51777429999947, "count": 116, "self": 85.48118848700506, "children": { "TorchPPOOptimizer.update": { "total": 69.03658581299442, "count": 6864, "self": 69.03658581299442 } } } } } } }, "trainer_threads": { "total": 1.0190001376031432e-06, "count": 1, "self": 1.0190001376031432e-06 }, "TrainerController._save_models": { "total": 0.14966402799973366, "count": 1, "self": 0.0012621479995686968, "children": { "RLTrainer._checkpoint": { "total": 0.14840188000016497, "count": 1, "self": 0.14840188000016497 } } } } } } }