{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41220033168792725, "min": 0.4114057719707489, "max": 1.569553017616272, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12286.8671875, "min": 12269.765625, "max": 47613.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5822389125823975, "min": -0.11498428136110306, "max": 0.6942797899246216, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.7736053466797, "min": -27.596227645874023, "max": 204.11825561523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.05193646624684334, "min": -0.06850093603134155, "max": 0.18614110350608826, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -14.698019981384277, "min": -18.700756072998047, "max": 44.673866271972656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06375282305425342, "min": 0.06375282305425342, "max": 0.07258593149114537, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.892539522759548, "min": 0.46785788376726634, "max": 1.0393452462934267, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018754684094222047, "min": 0.00018808710779223188, "max": 0.018754684094222047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2625655773191087, "min": 0.0020689581857145506, "max": 0.266464491491206, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.413226100385713e-06, "min": 7.413226100385713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010378516540539999, "min": 0.00010378516540539999, "max": 0.0032244478251840995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.09999999999999999, "min": 0.09999999999999996, "max": 0.10000000000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4, "min": 0.6999999999999998, "max": 1.5000000000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002568571814285714, "min": 0.0002568571814285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359600054, "min": 0.00359600054, "max": 0.10749410841, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013238899409770966, "min": 0.013238899409770966, "max": 0.2938432991504669, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18534459173679352, "min": 0.18534459173679352, "max": 2.056903123855591, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 304.03921568627453, "min": 295.3636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31012.0, "min": 15984.0, "max": 33058.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6394446354757235, "min": -1.0000000521540642, "max": 1.6844323035141435, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.86279745399952, "min": -32.000001668930054, "max": 173.2255982607603, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6394446354757235, "min": -1.0000000521540642, "max": 1.6844323035141435, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.86279745399952, "min": -32.000001668930054, "max": 173.2255982607603, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04125210204279249, "min": 0.04125210204279249, "max": 6.029717001132667, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.248966510407627, "min": 4.116219604853541, "max": 96.47547201812267, "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": "1695684100", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/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": "1695686579" }, "total": 2478.9873219500005, "count": 1, "self": 0.5271381610009485, "children": { "run_training.setup": { "total": 0.06174462199942354, "count": 1, "self": 0.06174462199942354 }, "TrainerController.start_learning": { "total": 2478.398439167, "count": 1, "self": 1.8160382739497436, "children": { "TrainerController._reset_env": { "total": 5.4108162129996344, "count": 1, "self": 5.4108162129996344 }, "TrainerController.advance": { "total": 2471.073005932052, "count": 63862, "self": 1.802593814994907, "children": { "env_step": { "total": 1767.4129801780864, "count": 63862, "self": 1633.3693659424298, "children": { "SubprocessEnvManager._take_step": { "total": 132.98010679175695, "count": 63862, "self": 5.5532069630671685, "children": { "TorchPolicy.evaluate": { "total": 127.42689982868978, "count": 62562, "self": 127.42689982868978 } } }, "workers": { "total": 1.0635074438996526, "count": 63862, "self": 0.0, "children": { "worker_root": { "total": 2472.2371925698244, "count": 63862, "is_parallel": true, "self": 973.5082063620321, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002957851999781269, "count": 1, "is_parallel": true, "self": 0.0008068369988905033, "children": { "_process_rank_one_or_two_observation": { "total": 0.002151015000890766, "count": 8, "is_parallel": true, "self": 0.002151015000890766 } } }, "UnityEnvironment.step": { "total": 0.062494325000443496, "count": 1, "is_parallel": true, "self": 0.0005603620011243038, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005146439998497954, "count": 1, "is_parallel": true, "self": 0.0005146439998497954 }, "communicator.exchange": { "total": 0.0584923609994803, "count": 1, "is_parallel": true, "self": 0.0584923609994803 }, "steps_from_proto": { "total": 0.0029269579999890993, "count": 1, "is_parallel": true, "self": 0.0004397669999889331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024871910000001662, "count": 8, "is_parallel": true, "self": 0.0024871910000001662 } } } } } } }, "UnityEnvironment.step": { "total": 1498.7289862077923, "count": 63861, "is_parallel": true, "self": 37.293954038740594, "children": { "UnityEnvironment._generate_step_input": { "total": 26.284392168064187, "count": 63861, "is_parallel": true, "self": 26.284392168064187 }, "communicator.exchange": { "total": 1313.6718675120255, "count": 63861, "is_parallel": true, "self": 1313.6718675120255 }, "steps_from_proto": { "total": 121.47877248896202, "count": 63861, "is_parallel": true, "self": 24.548256306333315, "children": { "_process_rank_one_or_two_observation": { "total": 96.93051618262871, "count": 510888, "is_parallel": true, "self": 96.93051618262871 } } } } } } } } } } }, "trainer_advance": { "total": 701.8574319389709, "count": 63862, "self": 3.213640973807742, "children": { "process_trajectory": { "total": 124.67974345216135, "count": 63862, "self": 124.37899267516241, "children": { "RLTrainer._checkpoint": { "total": 0.3007507769989388, "count": 2, "self": 0.3007507769989388 } } }, "_update_policy": { "total": 573.9640475130018, "count": 441, "self": 372.3691798989885, "children": { "TorchPPOOptimizer.update": { "total": 201.5948676140133, "count": 22899, "self": 201.5948676140133 } } } } } } }, "trainer_threads": { "total": 1.2029995559714735e-06, "count": 1, "self": 1.2029995559714735e-06 }, "TrainerController._save_models": { "total": 0.09857754499898874, "count": 1, "self": 0.0017244529990421142, "children": { "RLTrainer._checkpoint": { "total": 0.09685309199994663, "count": 1, "self": 0.09685309199994663 } } } } } } }