{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3167497217655182, "min": 0.3142779469490051, "max": 1.4187159538269043, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 9517.6953125, "min": 9362.96875, "max": 43038.16796875, "count": 36 }, "Pyramids.Step.mean": { "value": 1079996.0, "min": 29952.0, "max": 1079996.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079996.0, "min": 29952.0, "max": 1079996.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6993128061294556, "min": -0.13360926508903503, "max": 0.6993128061294556, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.1993408203125, "min": -32.06622314453125, "max": 204.1993408203125, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0063939341343939304, "min": -0.0011082031996920705, "max": 0.26560935378074646, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8670287132263184, "min": -0.30697229504585266, "max": 64.01185607910156, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06897275444366044, "min": 0.06455569300968174, "max": 0.07485355624443599, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9656185622112462, "min": 0.4968261029564604, "max": 1.081516011078801, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016269279376700512, "min": 0.00039122413577881486, "max": 0.016269279376700512, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2277699112738072, "min": 0.004303465493566964, "max": 0.2277699112738072, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.56690200587013e-06, "min": 9.56690200587013e-06, "max": 0.00029559148198898697, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00013393662808218183, "min": 0.00013393662808218183, "max": 0.003229146869072364, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10318893506493507, "min": 0.10318893506493507, "max": 0.19853049350649352, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4446450909090909, "min": 1.3897134545454546, "max": 2.488461090909091, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.0003285746129870131, "min": 0.0003285746129870131, "max": 0.009853196301298703, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.004600044581818183, "min": 0.004600044581818183, "max": 0.10767057996363635, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010096756741404533, "min": 0.010096756741404533, "max": 0.4189927279949188, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14135459065437317, "min": 0.14135459065437317, "max": 2.9329490661621094, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 262.9145299145299, "min": 262.9145299145299, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30761.0, "min": 15984.0, "max": 32983.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.703506879380037, "min": -1.0000000521540642, "max": 1.703506879380037, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 197.6067980080843, "min": -31.998401656746864, "max": 197.6067980080843, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.703506879380037, "min": -1.0000000521540642, "max": 1.703506879380037, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 197.6067980080843, "min": -31.998401656746864, "max": 197.6067980080843, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02739515269798897, "min": 0.02739515269798897, "max": 8.519620394334197, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1778377129667206, "min": 3.094784113127389, "max": 136.31392630934715, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683510271", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "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": "1683512767" }, "total": 2496.1267608, "count": 1, "self": 0.4739959649996308, "children": { "run_training.setup": { "total": 0.03676239100002476, "count": 1, "self": 0.03676239100002476 }, "TrainerController.start_learning": { "total": 2495.616002444, "count": 1, "self": 1.5458282540580512, "children": { "TrainerController._reset_env": { "total": 4.663729364999995, "count": 1, "self": 4.663729364999995 }, "TrainerController.advance": { "total": 2489.309611441942, "count": 70570, "self": 1.49815407890992, "children": { "env_step": { "total": 1804.6815188480432, "count": 70570, "self": 1686.90861883903, "children": { "SubprocessEnvManager._take_step": { "total": 116.85736459594523, "count": 70570, "self": 5.073376411991148, "children": { "TorchPolicy.evaluate": { "total": 111.78398818395408, "count": 68819, "self": 111.78398818395408 } } }, "workers": { "total": 0.915535413068028, "count": 70570, "self": 0.0, "children": { "worker_root": { "total": 2490.078786326926, "count": 70570, "is_parallel": true, "self": 924.8668152929517, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015301970000791698, "count": 1, "is_parallel": true, "self": 0.00038803499990081036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011421620001783594, "count": 8, "is_parallel": true, "self": 0.0011421620001783594 } } }, "UnityEnvironment.step": { "total": 0.08255859499990947, "count": 1, "is_parallel": true, "self": 0.0005956129998594406, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044429699994452676, "count": 1, "is_parallel": true, "self": 0.00044429699994452676 }, "communicator.exchange": { "total": 0.07750364800006082, "count": 1, "is_parallel": true, "self": 0.07750364800006082 }, "steps_from_proto": { "total": 0.0040150370000446856, "count": 1, "is_parallel": true, "self": 0.0003762540003435788, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036387829997011067, "count": 8, "is_parallel": true, "self": 0.0036387829997011067 } } } } } } }, "UnityEnvironment.step": { "total": 1565.2119710339744, "count": 70569, "is_parallel": true, "self": 34.15622666306399, "children": { "UnityEnvironment._generate_step_input": { "total": 24.151359611944144, "count": 70569, "is_parallel": true, "self": 24.151359611944144 }, "communicator.exchange": { "total": 1401.9938880179916, "count": 70569, "is_parallel": true, "self": 1401.9938880179916 }, "steps_from_proto": { "total": 104.91049674097451, "count": 70569, "is_parallel": true, "self": 21.34935956393565, "children": { "_process_rank_one_or_two_observation": { "total": 83.56113717703886, "count": 564552, "is_parallel": true, "self": 83.56113717703886 } } } } } } } } } } }, "trainer_advance": { "total": 683.1299385149885, "count": 70570, "self": 2.8530691289922743, "children": { "process_trajectory": { "total": 115.9511673059983, "count": 70570, "self": 115.69630558199833, "children": { "RLTrainer._checkpoint": { "total": 0.25486172399996576, "count": 2, "self": 0.25486172399996576 } } }, "_update_policy": { "total": 564.3257020799979, "count": 492, "self": 362.3699100640488, "children": { "TorchPPOOptimizer.update": { "total": 201.9557920159491, "count": 25137, "self": 201.9557920159491 } } } } } } }, "trainer_threads": { "total": 8.759998308960348e-07, "count": 1, "self": 8.759998308960348e-07 }, "TrainerController._save_models": { "total": 0.09683250700027202, "count": 1, "self": 0.0014135350006654335, "children": { "RLTrainer._checkpoint": { "total": 0.09541897199960658, "count": 1, "self": 0.09541897199960658 } } } } } } }