{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47983333468437195, "min": 0.47983333468437195, "max": 1.4709348678588867, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14302.8720703125, "min": 14302.8720703125, "max": 44622.28125, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29921.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29921.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5326857566833496, "min": -0.12270163744688034, "max": 0.5428873300552368, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.89053344726562, "min": -29.571094512939453, "max": 150.37979125976562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07180947065353394, "min": -0.827960193157196, "max": 0.6854439973831177, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.532176971435547, "min": -213.6137237548828, "max": 179.58633422851562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06510077609467164, "min": 0.06510077609467164, "max": 0.0738429471840857, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.911410865325403, "min": 0.5025571945247818, "max": 1.082230070004395, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015367443478247703, "min": 0.000651740787947865, "max": 0.3022251720962924, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21514420869546785, "min": 0.005865667091530785, "max": 4.231152409348094, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.472904651921429e-06, "min": 7.472904651921429e-06, "max": 0.00029523424444572854, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001046206651269, "min": 0.0001046206651269, "max": 0.0035066075311309, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024909357142857, "min": 0.1024909357142857, "max": 0.1984114142857143, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348731, "min": 1.3888799, "max": 2.5726031000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025884447785714284, "min": 0.00025884447785714284, "max": 0.009841300287142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00362382269, "min": 0.00362382269, "max": 0.11691002309, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009566998109221458, "min": 0.009566998109221458, "max": 0.35574573278427124, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13393796980381012, "min": 0.13393796980381012, "max": 2.490220069885254, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.58024691358025, "min": 336.5054945054945, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28478.0, "min": 16720.0, "max": 32929.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.549629615412818, "min": -0.9999750521965325, "max": 1.6426717141724152, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.51999884843826, "min": -31.99920167028904, "max": 151.1257977038622, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.549629615412818, "min": -0.9999750521965325, "max": 1.6426717141724152, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.51999884843826, "min": -31.99920167028904, "max": 151.1257977038622, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03478182537012653, "min": 0.03419445002098497, "max": 7.01534078138716, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.817327854980249, "min": 2.817327854980249, "max": 119.26079328358173, "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": "1721686261", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721688545" }, "total": 2284.1865258590005, "count": 1, "self": 5.783593502999793, "children": { "run_training.setup": { "total": 0.0657794090002426, "count": 1, "self": 0.0657794090002426 }, "TrainerController.start_learning": { "total": 2278.3371529470005, "count": 1, "self": 1.361925276146394, "children": { "TrainerController._reset_env": { "total": 57.45339011000033, "count": 1, "self": 57.45339011000033 }, "TrainerController.advance": { "total": 2218.223038735855, "count": 63688, "self": 1.4413362869972843, "children": { "env_step": { "total": 1550.801404013856, "count": 63688, "self": 1417.46170672495, "children": { "SubprocessEnvManager._take_step": { "total": 132.51426743894535, "count": 63688, "self": 4.770498969101027, "children": { "TorchPolicy.evaluate": { "total": 127.74376846984433, "count": 62556, "self": 127.74376846984433 } } }, "workers": { "total": 0.8254298499605284, "count": 63688, "self": 0.0, "children": { "worker_root": { "total": 2271.886685151704, "count": 63688, "is_parallel": true, "self": 978.5412025858604, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006243083000299521, "count": 1, "is_parallel": true, "self": 0.004688401001658349, "children": { "_process_rank_one_or_two_observation": { "total": 0.001554681998641172, "count": 8, "is_parallel": true, "self": 0.001554681998641172 } } }, "UnityEnvironment.step": { "total": 0.08378249799989135, "count": 1, "is_parallel": true, "self": 0.0006044839992682682, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004445670001587132, "count": 1, "is_parallel": true, "self": 0.0004445670001587132 }, "communicator.exchange": { "total": 0.0799159200005306, "count": 1, "is_parallel": true, "self": 0.0799159200005306 }, "steps_from_proto": { "total": 0.0028175269999337615, "count": 1, "is_parallel": true, "self": 0.0014275559997258824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013899710002078791, "count": 8, "is_parallel": true, "self": 0.0013899710002078791 } } } } } } }, "UnityEnvironment.step": { "total": 1293.3454825658437, "count": 63687, "is_parallel": true, "self": 33.46790104147476, "children": { "UnityEnvironment._generate_step_input": { "total": 22.6499894437693, "count": 63687, "is_parallel": true, "self": 22.6499894437693 }, "communicator.exchange": { "total": 1140.9830875760517, "count": 63687, "is_parallel": true, "self": 1140.9830875760517 }, "steps_from_proto": { "total": 96.24450450454788, "count": 63687, "is_parallel": true, "self": 19.451006265804608, "children": { "_process_rank_one_or_two_observation": { "total": 76.79349823874327, "count": 509496, "is_parallel": true, "self": 76.79349823874327 } } } } } } } } } } }, "trainer_advance": { "total": 665.9802984350017, "count": 63688, "self": 2.7244389988627518, "children": { "process_trajectory": { "total": 134.56065212017074, "count": 63688, "self": 131.99355629617003, "children": { "RLTrainer._checkpoint": { "total": 2.5670958240007167, "count": 2, "self": 2.5670958240007167 } } }, "_update_policy": { "total": 528.6952073159682, "count": 447, "self": 315.88849635403767, "children": { "TorchPPOOptimizer.update": { "total": 212.80671096193055, "count": 22821, "self": 212.80671096193055 } } } } } } }, "trainer_threads": { "total": 1.2389991752570495e-06, "count": 1, "self": 1.2389991752570495e-06 }, "TrainerController._save_models": { "total": 1.2987975859996368, "count": 1, "self": 1.1446847619990876, "children": { "RLTrainer._checkpoint": { "total": 0.15411282400054915, "count": 1, "self": 0.15411282400054915 } } } } } } }