{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32803598046302795, "min": 0.31065699458122253, "max": 1.4080204963684082, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9757.1025390625, "min": 9245.15234375, "max": 42713.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5701628923416138, "min": -0.09470613300800323, "max": 0.5701628923416138, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.92625427246094, "min": -22.91888427734375, "max": 161.92625427246094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006555818486958742, "min": -0.018487349152565002, "max": 0.3011987507343292, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8618524074554443, "min": -5.028558731079102, "max": 72.58889770507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06547037909331266, "min": 0.0652124868184201, "max": 0.07489496147792334, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9820556863996899, "min": 0.5162939932081921, "max": 1.0715519837685858, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017850920632352225, "min": 0.0011695900533622346, "max": 0.017850920632352225, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2677638094852834, "min": 0.014942314233970218, "max": 0.2677638094852834, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.471157509646661e-06, "min": 7.471157509646661e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011206736264469991, "min": 0.00011206736264469991, "max": 0.0033828191723937, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249035333333333, "min": 0.10249035333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373553, "min": 1.3886848, "max": 2.5276063, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025878629799999984, "min": 0.00025878629799999984, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038817944699999973, "min": 0.0038817944699999973, "max": 0.11278786937000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009251771494746208, "min": 0.00880469474941492, "max": 0.40506792068481445, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13877657055854797, "min": 0.12326572835445404, "max": 2.835475444793701, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 305.3578947368421, "min": 305.3578947368421, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29009.0, "min": 15984.0, "max": 33030.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.612387484094749, "min": -1.0000000521540642, "max": 1.612387484094749, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.7891984730959, "min": -30.689401648938656, "max": 154.7891984730959, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.612387484094749, "min": -1.0000000521540642, "max": 1.612387484094749, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.7891984730959, "min": -30.689401648938656, "max": 154.7891984730959, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02873739927645147, "min": 0.02873739927645147, "max": 7.933095519430935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.758790330539341, "min": 2.705439758632565, "max": 126.92952831089497, "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": "1711724312", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711727663" }, "total": 3351.493752533, "count": 1, "self": 0.7004167509999206, "children": { "run_training.setup": { "total": 0.06798957599994537, "count": 1, "self": 0.06798957599994537 }, "TrainerController.start_learning": { "total": 3350.7253462060003, "count": 1, "self": 2.2410491389882736, "children": { "TrainerController._reset_env": { "total": 3.31049828700003, "count": 1, "self": 3.31049828700003 }, "TrainerController.advance": { "total": 3345.091753343012, "count": 63853, "self": 2.6532423560602183, "children": { "env_step": { "total": 2247.283545811972, "count": 63853, "self": 2078.10220225791, "children": { "SubprocessEnvManager._take_step": { "total": 167.78450095800667, "count": 63853, "self": 7.137129368023295, "children": { "TorchPolicy.evaluate": { "total": 160.64737158998338, "count": 62557, "self": 160.64737158998338 } } }, "workers": { "total": 1.3968425960556488, "count": 63853, "self": 0.0, "children": { "worker_root": { "total": 3344.171026750019, "count": 63853, "is_parallel": true, "self": 1451.1277242449655, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007077594999998382, "count": 1, "is_parallel": true, "self": 0.004827194999961648, "children": { "_process_rank_one_or_two_observation": { "total": 0.002250400000036734, "count": 8, "is_parallel": true, "self": 0.002250400000036734 } } }, "UnityEnvironment.step": { "total": 0.06975659900001574, "count": 1, "is_parallel": true, "self": 0.0008005889999935789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005394070000193096, "count": 1, "is_parallel": true, "self": 0.0005394070000193096 }, "communicator.exchange": { "total": 0.06636601499997141, "count": 1, "is_parallel": true, "self": 0.06636601499997141 }, "steps_from_proto": { "total": 0.002050588000031439, "count": 1, "is_parallel": true, "self": 0.0005316340000263153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015189540000051238, "count": 8, "is_parallel": true, "self": 0.0015189540000051238 } } } } } } }, "UnityEnvironment.step": { "total": 1893.0433025050534, "count": 63852, "is_parallel": true, "self": 52.07784769098748, "children": { "UnityEnvironment._generate_step_input": { "total": 28.1077516219803, "count": 63852, "is_parallel": true, "self": 28.1077516219803 }, "communicator.exchange": { "total": 1680.0425125340398, "count": 63852, "is_parallel": true, "self": 1680.0425125340398 }, "steps_from_proto": { "total": 132.81519065804576, "count": 63852, "is_parallel": true, "self": 28.632330043085403, "children": { "_process_rank_one_or_two_observation": { "total": 104.18286061496036, "count": 510816, "is_parallel": true, "self": 104.18286061496036 } } } } } } } } } } }, "trainer_advance": { "total": 1095.1549651749795, "count": 63853, "self": 4.465817367983618, "children": { "process_trajectory": { "total": 165.97743800599886, "count": 63853, "self": 165.6474739329987, "children": { "RLTrainer._checkpoint": { "total": 0.3299640730001556, "count": 2, "self": 0.3299640730001556 } } }, "_update_policy": { "total": 924.7117098009969, "count": 450, "self": 363.3477507919903, "children": { "TorchPPOOptimizer.update": { "total": 561.3639590090066, "count": 22812, "self": 561.3639590090066 } } } } } } }, "trainer_threads": { "total": 1.041999894368928e-06, "count": 1, "self": 1.041999894368928e-06 }, "TrainerController._save_models": { "total": 0.08204439500013905, "count": 1, "self": 0.002024855999934516, "children": { "RLTrainer._checkpoint": { "total": 0.08001953900020453, "count": 1, "self": 0.08001953900020453 } } } } } } }