{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39007964730262756, "min": 0.39007964730262756, "max": 1.4313101768493652, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11546.357421875, "min": 11546.357421875, "max": 43420.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.569145143032074, "min": -0.09493271261453629, "max": 0.6658176779747009, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.6531982421875, "min": -22.8787841796875, "max": 194.24618530273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005202829837799072, "min": -0.00948827713727951, "max": 0.48604050278663635, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4411839246749878, "min": -2.5713231563568115, "max": 115.19159698486328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06903162507279333, "min": 0.06419442618769236, "max": 0.07291301597262431, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9664427510191066, "min": 0.4891955765581759, "max": 1.0359565366331178, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014301904888443892, "min": 0.0013636240519873835, "max": 0.017613208401598964, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2002266684382145, "min": 0.017727112675835984, "max": 0.2554347384527015, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.44798323165714e-06, "min": 7.44798323165714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010427176524319996, "min": 0.00010427176524319996, "max": 0.0036325324891558993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248262857142856, "min": 0.10248262857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347568, "min": 1.3886848, "max": 2.6108441, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002580145942857142, "min": 0.0002580145942857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036122043199999987, "min": 0.0036122043199999987, "max": 0.12110332559, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010755806230008602, "min": 0.010438631288707256, "max": 0.647458553314209, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15058128535747528, "min": 0.15058128535747528, "max": 4.532209873199463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.2926829268293, "min": 277.83620689655174, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27166.0, "min": 15984.0, "max": 33386.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5955170639222716, "min": -1.0000000521540642, "max": 1.6886961388473327, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.83239924162626, "min": -29.417601741850376, "max": 195.77039861679077, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5955170639222716, "min": -1.0000000521540642, "max": 1.6886961388473327, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.83239924162626, "min": -29.417601741850376, "max": 195.77039861679077, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03729154423224206, "min": 0.03181802893558252, "max": 14.680876759812236, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.057906627043849, "min": 3.057906627043849, "max": 234.89402815699577, "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": "1679132117", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679134355" }, "total": 2237.2870271419997, "count": 1, "self": 0.49314952999975503, "children": { "run_training.setup": { "total": 0.1045499080000809, "count": 1, "self": 0.1045499080000809 }, "TrainerController.start_learning": { "total": 2236.689327704, "count": 1, "self": 1.4638034699437412, "children": { "TrainerController._reset_env": { "total": 5.781389474999742, "count": 1, "self": 5.781389474999742 }, "TrainerController.advance": { "total": 2229.3454272930558, "count": 64052, "self": 1.5002008950650634, "children": { "env_step": { "total": 1589.7788561920452, "count": 64052, "self": 1475.531661475873, "children": { "SubprocessEnvManager._take_step": { "total": 113.37213210905202, "count": 64052, "self": 4.999922251127828, "children": { "TorchPolicy.evaluate": { "total": 108.37220985792419, "count": 62552, "self": 108.37220985792419 } } }, "workers": { "total": 0.8750626071200713, "count": 64052, "self": 0.0, "children": { "worker_root": { "total": 2231.5150218540043, "count": 64052, "is_parallel": true, "self": 877.9102417029994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018768750001072476, "count": 1, "is_parallel": true, "self": 0.0006603550009458559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012165199991613918, "count": 8, "is_parallel": true, "self": 0.0012165199991613918 } } }, "UnityEnvironment.step": { "total": 0.046280665999802295, "count": 1, "is_parallel": true, "self": 0.0005164009994587104, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000504741999975522, "count": 1, "is_parallel": true, "self": 0.000504741999975522 }, "communicator.exchange": { "total": 0.043580800000199815, "count": 1, "is_parallel": true, "self": 0.043580800000199815 }, "steps_from_proto": { "total": 0.0016787230001682474, "count": 1, "is_parallel": true, "self": 0.0003681710009004746, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013105519992677728, "count": 8, "is_parallel": true, "self": 0.0013105519992677728 } } } } } } }, "UnityEnvironment.step": { "total": 1353.604780151005, "count": 64051, "is_parallel": true, "self": 31.376816915067593, "children": { "UnityEnvironment._generate_step_input": { "total": 24.440755797995735, "count": 64051, "is_parallel": true, "self": 24.440755797995735 }, "communicator.exchange": { "total": 1200.3159996269055, "count": 64051, "is_parallel": true, "self": 1200.3159996269055 }, "steps_from_proto": { "total": 97.47120781103604, "count": 64051, "is_parallel": true, "self": 21.102433500889674, "children": { "_process_rank_one_or_two_observation": { "total": 76.36877431014636, "count": 512408, "is_parallel": true, "self": 76.36877431014636 } } } } } } } } } } }, "trainer_advance": { "total": 638.0663702059455, "count": 64052, "self": 2.6996300689775126, "children": { "process_trajectory": { "total": 123.44357178397149, "count": 64052, "self": 123.11635056497153, "children": { "RLTrainer._checkpoint": { "total": 0.32722121899996637, "count": 2, "self": 0.32722121899996637 } } }, "_update_policy": { "total": 511.9231683529965, "count": 455, "self": 326.32215405903435, "children": { "TorchPPOOptimizer.update": { "total": 185.60101429396218, "count": 22827, "self": 185.60101429396218 } } } } } } }, "trainer_threads": { "total": 1.0510002539376728e-06, "count": 1, "self": 1.0510002539376728e-06 }, "TrainerController._save_models": { "total": 0.09870641500037891, "count": 1, "self": 0.0018483070007278002, "children": { "RLTrainer._checkpoint": { "total": 0.09685810799965111, "count": 1, "self": 0.09685810799965111 } } } } } } }