{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19172492623329163, "min": 0.18205031752586365, "max": 1.574824333190918, "count": 200 }, "Pyramids.Policy.Entropy.sum": { "value": 1920.31689453125, "min": 1817.59033203125, "max": 16126.201171875, "count": 200 }, "Pyramids.Step.mean": { "value": 1999982.0, "min": 9984.0, "max": 1999982.0, "count": 200 }, "Pyramids.Step.sum": { "value": 1999982.0, "min": 9984.0, "max": 1999982.0, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6092286705970764, "min": -0.11836113035678864, "max": 0.7274836897850037, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.658267974853516, "min": -9.567208290100098, "max": 68.38346862792969, "count": 200 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028318719938397408, "min": -0.025536684319376945, "max": 0.7939819693565369, "count": 200 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.633641004562378, "min": -2.349375009536743, "max": 64.31253814697266, "count": 200 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06779724450219267, "min": 0.05861376399795214, "max": 0.08010646419764575, "count": 200 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2711889780087707, "min": 0.13946829208951636, "max": 0.3866953164494286, "count": 200 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0228228047247588, "min": 0.0003552941129176664, "max": 0.026594037141573303, "count": 200 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0912912188990352, "min": 0.0014211764516706656, "max": 0.09787206737867866, "count": 200 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.283497572499998e-07, "min": 7.283497572499998e-07, "max": 0.00029907840030719997, "count": 200 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.9133990289999993e-06, "min": 2.9133990289999993e-06, "max": 0.0014064471311842999, "count": 200 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10024274999999999, "min": 0.10024274999999999, "max": 0.1996928, "count": 200 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.40097099999999997, "min": 0.39458560000000004, "max": 0.9688157, "count": 200 }, "Pyramids.Policy.Beta.mean": { "value": 3.4250724999999996e-05, "min": 3.4250724999999996e-05, "max": 0.00996931072, "count": 200 }, "Pyramids.Policy.Beta.sum": { "value": 0.00013700289999999998, "min": 0.00013700289999999998, "max": 0.04688468843, "count": 200 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009591388516128063, "min": 0.009055763483047485, "max": 1.3096299171447754, "count": 200 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.03836555406451225, "min": 0.0370219424366951, "max": 2.619259834289551, "count": 200 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.8285714285714, "min": 250.5483870967742, "max": 999.0, "count": 196 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 11719.0, "min": 468.0, "max": 15984.0, "count": 196 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4965999849578913, "min": -1.0000000521540642, "max": 1.7380302905133276, "count": 196 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 50.884399488568306, "min": -16.000000834465027, "max": 64.29899881780148, "count": 196 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4965999849578913, "min": -1.0000000521540642, "max": 1.7380302905133276, "count": 196 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 50.884399488568306, "min": -16.000000834465027, "max": 64.29899881780148, "count": 196 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033111502344528324, "min": 0.024485624249791726, "max": 15.531710676848888, "count": 196 }, "Pyramids.Policy.RndReward.sum": { "value": 1.125791079713963, "min": 0.47632402181625366, "max": 248.50737082958221, "count": 196 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688633466", "python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]", "command_line_arguments": "/opt/conda/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688638607" }, "total": 5140.883329271999, "count": 1, "self": 0.4802718310002092, "children": { "run_training.setup": { "total": 0.10473302499985948, "count": 1, "self": 0.10473302499985948 }, "TrainerController.start_learning": { "total": 5140.298324416, "count": 1, "self": 3.104235193889508, "children": { "TrainerController._reset_env": { "total": 5.924722757999916, "count": 1, "self": 5.924722757999916 }, "TrainerController.advance": { "total": 5131.15884783411, "count": 128128, "self": 3.0738365509560026, "children": { "env_step": { "total": 3407.3900670700855, "count": 128128, "self": 3183.857549606828, "children": { "SubprocessEnvManager._take_step": { "total": 221.5426570562763, "count": 128128, "self": 10.123844117245426, "children": { "TorchPolicy.evaluate": { "total": 211.4188129390309, "count": 125069, "self": 211.4188129390309 } } }, "workers": { "total": 1.989860406981279, "count": 128128, "self": 0.0, "children": { "worker_root": { "total": 5128.110874648076, "count": 128128, "is_parallel": true, "self": 2216.3080968071813, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022757220003768452, "count": 1, "is_parallel": true, "self": 0.0006742210007359972, "children": { "_process_rank_one_or_two_observation": { "total": 0.001601500999640848, "count": 8, "is_parallel": true, "self": 0.001601500999640848 } } }, "UnityEnvironment.step": { "total": 0.05466452400014532, "count": 1, "is_parallel": true, "self": 0.0006696730001749529, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006374100003085914, "count": 1, "is_parallel": true, "self": 0.0006374100003085914 }, "communicator.exchange": { "total": 0.05115079000006517, "count": 1, "is_parallel": true, "self": 0.05115079000006517 }, "steps_from_proto": { "total": 0.0022066509995966044, "count": 1, "is_parallel": true, "self": 0.00042243700045219157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017842139991444128, "count": 8, "is_parallel": true, "self": 0.0017842139991444128 } } } } } } }, "UnityEnvironment.step": { "total": 2911.8027778408946, "count": 128127, "is_parallel": true, "self": 77.63013123565952, "children": { "UnityEnvironment._generate_step_input": { "total": 65.0155412532622, "count": 128127, "is_parallel": true, "self": 65.0155412532622 }, "communicator.exchange": { "total": 2494.009405991997, "count": 128127, "is_parallel": true, "self": 2494.009405991997 }, "steps_from_proto": { "total": 275.14769935997583, "count": 128127, "is_parallel": true, "self": 51.47826672801011, "children": { "_process_rank_one_or_two_observation": { "total": 223.66943263196572, "count": 1025016, "is_parallel": true, "self": 223.66943263196572 } } } } } } } } } } }, "trainer_advance": { "total": 1720.694944213068, "count": 128128, "self": 5.558579964822911, "children": { "process_trajectory": { "total": 298.37806646624176, "count": 128128, "self": 297.9187499182408, "children": { "RLTrainer._checkpoint": { "total": 0.4593165480009702, "count": 4, "self": 0.4593165480009702 } } }, "_update_policy": { "total": 1416.7582977820034, "count": 918, "self": 1034.3793843329645, "children": { "TorchPPOOptimizer.update": { "total": 382.3789134490389, "count": 45531, "self": 382.3789134490389 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.11051763500017842, "count": 1, "self": 0.00130140900000697, "children": { "RLTrainer._checkpoint": { "total": 0.10921622600017145, "count": 1, "self": 0.10921622600017145 } } } } } } }