{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7061400413513184, "min": 0.7061400413513184, "max": 1.5146020650863647, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 21150.306640625, "min": 21150.306640625, "max": 45946.96875, "count": 10 }, "Pyramids.Step.mean": { "value": 299932.0, "min": 29952.0, "max": 299932.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299932.0, "min": 29952.0, "max": 299932.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08245431631803513, "min": -0.1067349836230278, "max": -0.05047430098056793, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.78903579711914, "min": -25.616395950317383, "max": -12.214780807495117, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.039111312478780746, "min": 0.039111312478780746, "max": 0.38477909564971924, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.386714935302734, "min": 9.386714935302734, "max": 91.19264221191406, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06939178104282548, "min": 0.06582274968446042, "max": 0.07301165310236767, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9020931535567313, "min": 0.4798236180996073, "max": 0.9020931535567313, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0007119372186195668, "min": 0.0002428228409316624, "max": 0.009110999507876322, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.009255183842054369, "min": 0.0026710512502482863, "max": 0.06377699655513426, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.555917173671795e-05, "min": 1.555917173671795e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00020226923257733335, "min": 0.00020226923257733335, "max": 0.0027081002973, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10518635897435898, "min": 0.10518635897435898, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3674226666666667, "min": 1.362282666666667, "max": 2.1027000000000005, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005281172615384616, "min": 0.0005281172615384616, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.0068655244000000015, "min": 0.0068655244000000015, "max": 0.09029973000000001, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.033588189631700516, "min": 0.033588189631700516, "max": 0.4117766320705414, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4366464614868164, "min": 0.4366464614868164, "max": 2.882436513900757, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 995.1290322580645, "min": 938.125, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30849.0, "min": 15984.0, "max": 32735.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9314581184617935, "min": -1.0000000521540642, "max": -0.7722250490138928, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.875201672315598, "min": -31.9992016851902, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9314581184617935, "min": -1.0000000521540642, "max": -0.7722250490138928, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.875201672315598, "min": -31.9992016851902, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.34920530682129247, "min": 0.34920530682129247, "max": 8.641915165819228, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 10.825364511460066, "min": 9.322875704616308, "max": 138.27064265310764, "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": "1788424113", "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": "1788424485" }, "total": 372.12205932899997, "count": 1, "self": 0.2710099949990763, "children": { "run_training.setup": { "total": 0.018006019000495144, "count": 1, "self": 0.018006019000495144 }, "TrainerController.start_learning": { "total": 371.8330433150004, "count": 1, "self": 0.2512422379149939, "children": { "TrainerController._reset_env": { "total": 1.278217976999258, "count": 1, "self": 1.278217976999258 }, "TrainerController.advance": { "total": 370.2450190770869, "count": 18856, "self": 0.2754722609961391, "children": { "env_step": { "total": 244.51709868805392, "count": 18856, "self": 225.1924428669936, "children": { "SubprocessEnvManager._take_step": { "total": 19.152604208064986, "count": 18856, "self": 0.8570362050659242, "children": { "TorchPolicy.evaluate": { "total": 18.29556800299906, "count": 18802, "self": 18.29556800299906 } } }, "workers": { "total": 0.17205161299534666, "count": 18856, "self": 0.0, "children": { "worker_root": { "total": 371.16828448495926, "count": 18856, "is_parallel": true, "self": 167.12529618199096, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010653700001057587, "count": 1, "is_parallel": true, "self": 0.0003001400009452482, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007652299991605105, "count": 8, "is_parallel": true, "self": 0.0007652299991605105 } } }, "UnityEnvironment.step": { "total": 0.028350837999823852, "count": 1, "is_parallel": true, "self": 0.00023595999937242595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003385300005902536, "count": 1, "is_parallel": true, "self": 0.0003385300005902536 }, "communicator.exchange": { "total": 0.027001607999409316, "count": 1, "is_parallel": true, "self": 0.027001607999409316 }, "steps_from_proto": { "total": 0.0007747400004518568, "count": 1, "is_parallel": true, "self": 0.00019938000150432345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005753599989475333, "count": 8, "is_parallel": true, "self": 0.0005753599989475333 } } } } } } }, "UnityEnvironment.step": { "total": 204.0429883029683, "count": 18855, "is_parallel": true, "self": 4.528923898043104, "children": { "UnityEnvironment._generate_step_input": { "total": 3.394646311992801, "count": 18855, "is_parallel": true, "self": 3.394646311992801 }, "communicator.exchange": { "total": 182.29412659499758, "count": 18855, "is_parallel": true, "self": 182.29412659499758 }, "steps_from_proto": { "total": 13.825291497934813, "count": 18855, "is_parallel": true, "self": 3.0794088549910157, "children": { "_process_rank_one_or_two_observation": { "total": 10.745882642943798, "count": 150840, "is_parallel": true, "self": 10.745882642943798 } } } } } } } } } } }, "trainer_advance": { "total": 125.45244812803685, "count": 18856, "self": 0.3730359030478212, "children": { "process_trajectory": { "total": 20.92103096498522, "count": 18856, "self": 20.92103096498522 }, "_update_policy": { "total": 104.15838126000381, "count": 114, "self": 53.069728763977764, "children": { "TorchPPOOptimizer.update": { "total": 51.08865249602604, "count": 6864, "self": 51.08865249602604 } } } } } } }, "trainer_threads": { "total": 8.089991752058268e-07, "count": 1, "self": 8.089991752058268e-07 }, "TrainerController._save_models": { "total": 0.058563214000059816, "count": 1, "self": 0.0007708889997957158, "children": { "RLTrainer._checkpoint": { "total": 0.0577923250002641, "count": 1, "self": 0.0577923250002641 } } } } } } }