{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19532400369644165, "min": 0.19176672399044037, "max": 1.431990623474121, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 5875.34619140625, "min": 5722.31884765625, "max": 43440.8671875, "count": 50 }, "Pyramids.Step.mean": { "value": 1499929.0, "min": 29952.0, "max": 1499929.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499929.0, "min": 29952.0, "max": 1499929.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8025957942008972, "min": -0.09869258105754852, "max": 0.8025957942008972, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 243.98912048339844, "min": -23.982297897338867, "max": 243.98912048339844, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010153330862522125, "min": -0.007649863604456186, "max": 0.5776370763778687, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0866127014160156, "min": -2.1419618129730225, "max": 136.89999389648438, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06757387201845025, "min": 0.06485950882086486, "max": 0.07370327567884065, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0136080802767538, "min": 0.5089080015440932, "max": 1.0536614030327958, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014148789550138947, "min": 0.0008208262323227651, "max": 0.016990357592045813, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2122318432520842, "min": 0.009849914787873181, "max": 0.2391615626014148, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.9594723468755577e-06, "min": 2.9594723468755577e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.4392085203133365e-05, "min": 4.4392085203133365e-05, "max": 0.0038223127258957997, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10098645777777779, "min": 0.10098645777777779, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.514796866666667, "min": 1.3924565333333336, "max": 2.6741041999999995, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010854713200000004, "min": 0.00010854713200000004, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0016282069800000007, "min": 0.0016282069800000007, "max": 0.12742300957999997, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012307985685765743, "min": 0.012307985685765743, "max": 0.6702824831008911, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18461978435516357, "min": 0.17698363959789276, "max": 4.691977500915527, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.97619047619048, "min": 229.45736434108528, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28977.0, "min": 15984.0, "max": 32550.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.770023800432682, "min": -1.0000000521540642, "max": 1.770023800432682, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 223.02299885451794, "min": -29.86300168186426, "max": 226.51599816977978, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.770023800432682, "min": -1.0000000521540642, "max": 1.770023800432682, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 223.02299885451794, "min": -29.86300168186426, "max": 226.51599816977978, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029647420209094267, "min": 0.029647420209094267, "max": 12.51437996700406, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 3.735574946345878, "min": 3.735574946345878, "max": 200.23007947206497, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730961208", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/root/miniconda3/envs/pyramids2/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./Pyramids --run-id=Pyramids Training --results-dir=./results --no-graphics --base-port=6005", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1730965705" }, "total": 4224.695456683, "count": 1, "self": 1.1911924490004822, "children": { "run_training.setup": { "total": 0.06859295999993265, "count": 1, "self": 0.06859295999993265 }, "TrainerController.start_learning": { "total": 4223.435671274, "count": 1, "self": 2.1002487250025297, "children": { "TrainerController._reset_env": { "total": 20.490043730999787, "count": 1, "self": 20.490043730999787 }, "TrainerController.advance": { "total": 4200.702905977998, "count": 96801, "self": 2.142794361028791, "children": { "env_step": { "total": 2522.388875197892, "count": 96801, "self": 2093.626724642923, "children": { "SubprocessEnvManager._take_step": { "total": 427.35822932516476, "count": 96801, "self": 7.878471373166576, "children": { "TorchPolicy.evaluate": { "total": 419.4797579519982, "count": 93815, "self": 419.4797579519982 } } }, "workers": { "total": 1.4039212298043822, "count": 96801, "self": 0.0, "children": { "worker_root": { "total": 4218.280266425885, "count": 96801, "is_parallel": true, "self": 2282.143642674496, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007872373999816773, "count": 1, "is_parallel": true, "self": 0.005579013999977178, "children": { "_process_rank_one_or_two_observation": { "total": 0.002293359999839595, "count": 8, "is_parallel": true, "self": 0.002293359999839595 } } }, "UnityEnvironment.step": { "total": 0.07592517500006579, "count": 1, "is_parallel": true, "self": 0.0008168600002136372, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009182529997815436, "count": 1, "is_parallel": true, "self": 0.0009182529997815436 }, "communicator.exchange": { "total": 0.07289752699989549, "count": 1, "is_parallel": true, "self": 0.07289752699989549 }, "steps_from_proto": { "total": 0.0012925350001751212, "count": 1, "is_parallel": true, "self": 0.0003405869997550326, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009519480004200886, "count": 8, "is_parallel": true, "self": 0.0009519480004200886 } } } } } } }, "UnityEnvironment.step": { "total": 1936.1366237513894, "count": 96800, "is_parallel": true, "self": 29.34667341645263, "children": { "UnityEnvironment._generate_step_input": { "total": 23.169359972988786, "count": 96800, "is_parallel": true, "self": 23.169359972988786 }, "communicator.exchange": { "total": 1786.8466746432405, "count": 96800, "is_parallel": true, "self": 1786.8466746432405 }, "steps_from_proto": { "total": 96.77391571870749, "count": 96800, "is_parallel": true, "self": 23.00106582061926, "children": { "_process_rank_one_or_two_observation": { "total": 73.77284989808823, "count": 774400, "is_parallel": true, "self": 73.77284989808823 } } } } } } } } } } }, "trainer_advance": { "total": 1676.171236419077, "count": 96801, "self": 4.071546576061792, "children": { "process_trajectory": { "total": 246.64640003601926, "count": 96801, "self": 245.84998928601817, "children": { "RLTrainer._checkpoint": { "total": 0.7964107500010869, "count": 3, "self": 0.7964107500010869 } } }, "_update_policy": { "total": 1425.453289806996, "count": 690, "self": 550.4882944030546, "children": { "TorchPPOOptimizer.update": { "total": 874.9649954039414, "count": 34224, "self": 874.9649954039414 } } } } } } }, "trainer_threads": { "total": 8.429997251369059e-07, "count": 1, "self": 8.429997251369059e-07 }, "TrainerController._save_models": { "total": 0.14247199700002966, "count": 1, "self": 0.0013185789994167862, "children": { "RLTrainer._checkpoint": { "total": 0.14115341800061287, "count": 1, "self": 0.14115341800061287 } } } } } } }