{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18183214962482452, "min": 0.17495185136795044, "max": 1.4631847143173218, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5463.6923828125, "min": 5245.75634765625, "max": 44387.171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999948.0, "min": 29952.0, "max": 2999948.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999948.0, "min": 29952.0, "max": 2999948.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8318068981170654, "min": -0.10318829119205475, "max": 0.8318068981170654, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 253.70111083984375, "min": -24.868377685546875, "max": 253.70111083984375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.029915275052189827, "min": -0.030223090201616287, "max": 0.46151572465896606, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.12415885925293, "min": -9.12415885925293, "max": 109.37922668457031, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06846809357652785, "min": 0.06437604190277572, "max": 0.07525510133994275, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9585533100713899, "min": 0.4837875268289929, "max": 1.0754419976777476, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015027535109159844, "min": 0.0007051365999425249, "max": 0.01674702243083933, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21038549152823782, "min": 0.009871912399195349, "max": 0.2344583140317506, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5705851907904756e-06, "min": 1.5705851907904756e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.198819267106666e-05, "min": 2.198819267106666e-05, "max": 0.004072331942556066, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052349523809526, "min": 0.10052349523809526, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073289333333336, "min": 1.3962282666666668, "max": 2.8574439333333332, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.229717428571427e-05, "min": 6.229717428571427e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008721604399999998, "min": 0.0008721604399999998, "max": 0.13575864894, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004802223294973373, "min": 0.004341320600360632, "max": 0.4604782164096832, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06723112612962723, "min": 0.06077848747372627, "max": 3.2233474254608154, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.86029411764707, "min": 223.86029411764707, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30445.0, "min": 15984.0, "max": 32705.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.775794103522511, "min": -1.0000000521540642, "max": 1.775794103522511, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 241.5079980790615, "min": -28.715201556682587, "max": 241.5079980790615, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.775794103522511, "min": -1.0000000521540642, "max": 1.775794103522511, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 241.5079980790615, "min": -28.715201556682587, "max": 241.5079980790615, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011192960254073328, "min": 0.011192960254073328, "max": 9.208604524843395, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5222425945539726, "min": 1.3224208976453156, "max": 147.33767239749432, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720931018", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720943036" }, "total": 12018.200216583, "count": 1, "self": 0.8519757680023758, "children": { "run_training.setup": { "total": 0.08246981499996764, "count": 1, "self": 0.08246981499996764 }, "TrainerController.start_learning": { "total": 12017.265770999998, "count": 1, "self": 7.554509299900019, "children": { "TrainerController._reset_env": { "total": 3.2070054219998383, "count": 1, "self": 3.2070054219998383 }, "TrainerController.advance": { "total": 12006.409005813097, "count": 194682, "self": 8.225648488045408, "children": { "env_step": { "total": 8333.943111293058, "count": 194682, "self": 7789.472813091694, "children": { "SubprocessEnvManager._take_step": { "total": 539.7516577280708, "count": 194682, "self": 25.11201704507903, "children": { "TorchPolicy.evaluate": { "total": 514.6396406829917, "count": 187559, "self": 514.6396406829917 } } }, "workers": { "total": 4.718640473292908, "count": 194682, "self": 0.0, "children": { "worker_root": { "total": 11990.831805367303, "count": 194682, "is_parallel": true, "self": 4834.779586855091, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036214349997862882, "count": 1, "is_parallel": true, "self": 0.001216506000218942, "children": { "_process_rank_one_or_two_observation": { "total": 0.002404928999567346, "count": 8, "is_parallel": true, "self": 0.002404928999567346 } } }, "UnityEnvironment.step": { "total": 0.06577944100035893, "count": 1, "is_parallel": true, "self": 0.000837136000427563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005615350000880426, "count": 1, "is_parallel": true, "self": 0.0005615350000880426 }, "communicator.exchange": { "total": 0.062350263000098494, "count": 1, "is_parallel": true, "self": 0.062350263000098494 }, "steps_from_proto": { "total": 0.00203050699974483, "count": 1, "is_parallel": true, "self": 0.0004233529989505769, "children": { "_process_rank_one_or_two_observation": { "total": 0.001607154000794253, "count": 8, "is_parallel": true, "self": 0.001607154000794253 } } } } } } }, "UnityEnvironment.step": { "total": 7156.052218512212, "count": 194681, "is_parallel": true, "self": 167.3935752350826, "children": { "UnityEnvironment._generate_step_input": { "total": 99.72388902974308, "count": 194681, "is_parallel": true, "self": 99.72388902974308 }, "communicator.exchange": { "total": 6463.16625916617, "count": 194681, "is_parallel": true, "self": 6463.16625916617 }, "steps_from_proto": { "total": 425.76849508121586, "count": 194681, "is_parallel": true, "self": 93.57789963261484, "children": { "_process_rank_one_or_two_observation": { "total": 332.190595448601, "count": 1557448, "is_parallel": true, "self": 332.190595448601 } } } } } } } } } } }, "trainer_advance": { "total": 3664.2402460319945, "count": 194682, "self": 16.18541748014468, "children": { "process_trajectory": { "total": 567.5055838228386, "count": 194682, "self": 566.9276987228372, "children": { "RLTrainer._checkpoint": { "total": 0.5778851000013674, "count": 6, "self": 0.5778851000013674 } } }, "_update_policy": { "total": 3080.549244729011, "count": 1402, "self": 1227.5088514239187, "children": { "TorchPPOOptimizer.update": { "total": 1853.0403933050925, "count": 68322, "self": 1853.0403933050925 } } } } } } }, "trainer_threads": { "total": 1.4060005923965946e-06, "count": 1, "self": 1.4060005923965946e-06 }, "TrainerController._save_models": { "total": 0.09524905900070735, "count": 1, "self": 0.0030239010011428036, "children": { "RLTrainer._checkpoint": { "total": 0.09222515799956454, "count": 1, "self": 0.09222515799956454 } } } } } } }