{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.449701726436615, "min": 0.449701726436615, "max": 1.4280096292495728, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13634.9560546875, "min": 13634.9560546875, "max": 43320.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40966179966926575, "min": -0.09639322012662888, "max": 0.4709737002849579, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.60868835449219, "min": -23.327159881591797, "max": 127.05229187011719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004913768731057644, "min": -0.007100201211869717, "max": 0.3013646900653839, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3267176151275635, "min": -1.874453067779541, "max": 71.42343139648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681662009905858, "min": 0.06526270886739191, "max": 0.07360263431663408, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9543268138682013, "min": 0.5011534766152222, "max": 1.070489668144671, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014694889709398692, "min": 0.0004235745644795499, "max": 0.014769917707044873, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20572845593158168, "min": 0.005930043902713698, "max": 0.20677884789862822, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4118332437071475e-06, "min": 7.4118332437071475e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010376566541190007, "min": 0.00010376566541190007, "max": 0.0036322630892457, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247057857142859, "min": 0.10247057857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345881000000003, "min": 1.3886848, "max": 2.6107543000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025681079928571444, "min": 0.00025681079928571444, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035953511900000024, "min": 0.0035953511900000024, "max": 0.12109435457, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009917506016790867, "min": 0.009917506016790867, "max": 0.4148555099964142, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13884508609771729, "min": 0.13884508609771729, "max": 2.9039885997772217, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.85135135135135, "min": 394.23376623376623, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29959.0, "min": 15984.0, "max": 32877.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4058999721262906, "min": -1.0000000521540642, "max": 1.5017131285643892, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.0365979373455, "min": -30.666801653802395, "max": 114.13019777089357, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4058999721262906, "min": -1.0000000521540642, "max": 1.5017131285643892, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.0365979373455, "min": -30.666801653802395, "max": 114.13019777089357, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04125636693670704, "min": 0.04125636693670704, "max": 8.458495073020458, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.052971153316321, "min": 3.052971153316321, "max": 135.33592116832733, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1668153153", "python_version": "3.8.13 | packaged by conda-forge | (default, Mar 25 2022, 06:04:10) \n[GCC 10.3.0]", "command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.3", "end_time_seconds": "1668156146" }, "total": 2993.159958376549, "count": 1, "self": 0.8303574761375785, "children": { "run_training.setup": { "total": 0.17639728263020515, "count": 1, "self": 0.17639728263020515 }, "TrainerController.start_learning": { "total": 2992.1532036177814, "count": 1, "self": 1.105168977752328, "children": { "TrainerController._reset_env": { "total": 5.922881801612675, "count": 1, "self": 5.922881801612675 }, "TrainerController.advance": { "total": 2984.981429251842, "count": 63575, "self": 1.0910676680505276, "children": { "env_step": { "total": 1969.355714276433, "count": 63575, "self": 1874.520522115752, "children": { "SubprocessEnvManager._take_step": { "total": 94.12087427638471, "count": 63575, "self": 3.902109225280583, "children": { "TorchPolicy.evaluate": { "total": 90.21876505110413, "count": 62564, "self": 30.958266763947904, "children": { "TorchPolicy.sample_actions": { "total": 59.260498287156224, "count": 62564, "self": 59.260498287156224 } } } } }, "workers": { "total": 0.7143178842961788, "count": 63575, "self": 0.0, "children": { "worker_root": { "total": 2987.8581345360726, "count": 63575, "is_parallel": true, "self": 1236.599324947223, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0045655835419893265, "count": 1, "is_parallel": true, "self": 0.0014189807698130608, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031466027721762657, "count": 8, "is_parallel": true, "self": 0.0031466027721762657 } } }, "UnityEnvironment.step": { "total": 0.06641075946390629, "count": 1, "is_parallel": true, "self": 0.0008928673341870308, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007423553615808487, "count": 1, "is_parallel": true, "self": 0.0007423553615808487 }, "communicator.exchange": { "total": 0.062159025110304356, "count": 1, "is_parallel": true, "self": 0.062159025110304356 }, "steps_from_proto": { "total": 0.002616511657834053, "count": 1, "is_parallel": true, "self": 0.0006196461617946625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019968654960393906, "count": 8, "is_parallel": true, "self": 0.0019968654960393906 } } } } } } }, "UnityEnvironment.step": { "total": 1751.2588095888495, "count": 63574, "is_parallel": true, "self": 52.18478089570999, "children": { "UnityEnvironment._generate_step_input": { "total": 36.879492323845625, "count": 63574, "is_parallel": true, "self": 36.879492323845625 }, "communicator.exchange": { "total": 1508.8757964856923, "count": 63574, "is_parallel": true, "self": 1508.8757964856923 }, "steps_from_proto": { "total": 153.31873988360167, "count": 63574, "is_parallel": true, "self": 34.31051422748715, "children": { "_process_rank_one_or_two_observation": { "total": 119.00822565611452, "count": 508592, "is_parallel": true, "self": 119.00822565611452 } } } } } } } } } } }, "trainer_advance": { "total": 1014.5346473073587, "count": 63575, "self": 2.1868025586009026, "children": { "process_trajectory": { "total": 130.35874030645937, "count": 63575, "self": 130.04567389562726, "children": { "RLTrainer._checkpoint": { "total": 0.31306641083210707, "count": 2, "self": 0.31306641083210707 } } }, "_update_policy": { "total": 881.9891044422984, "count": 449, "self": 215.5706182140857, "children": { "TorchPPOOptimizer.update": { "total": 666.4184862282127, "count": 22839, "self": 666.4184862282127 } } } } } } }, "trainer_threads": { "total": 9.927898645401e-07, "count": 1, "self": 9.927898645401e-07 }, "TrainerController._save_models": { "total": 0.14372259378433228, "count": 1, "self": 0.008248788304626942, "children": { "RLTrainer._checkpoint": { "total": 0.13547380547970533, "count": 1, "self": 0.13547380547970533 } } } } } } }