{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20591500401496887, "min": 0.20291799306869507, "max": 1.5050634145736694, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 6124.73583984375, "min": 6055.07275390625, "max": 45657.60546875, "count": 66 }, "Pyramids.Step.mean": { "value": 1979924.0, "min": 29952.0, "max": 1979924.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979924.0, "min": 29952.0, "max": 1979924.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6699345111846924, "min": -0.14441245794296265, "max": 0.744976282119751, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 188.92152404785156, "min": -34.22575378417969, "max": 217.53306579589844, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.033292945474386215, "min": -0.007763184607028961, "max": 0.33629462122917175, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.38861083984375, "min": -2.08829665184021, "max": 79.70182800292969, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06762650432176001, "min": 0.06458378818208295, "max": 0.07625083543517652, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9467710605046402, "min": 0.483862910179345, "max": 1.0774932005351372, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01544021334709777, "min": 0.00012389423192813137, "max": 0.017092863967477837, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21616298685936877, "min": 0.001362836551209445, "max": 0.23930009554468973, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.298537519567857e-06, "min": 5.298537519567857e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.417952527395e-05, "min": 7.417952527395e-05, "max": 0.0035379395206868993, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10176614642857143, "min": 0.10176614642857143, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.42472605, "min": 1.3845568000000001, "max": 2.6511281500000003, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001864380282142857, "min": 0.0001864380282142857, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.002610132395, "min": 0.002610132395, "max": 0.11795337869000001, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008993481285870075, "min": 0.008688977919518948, "max": 0.43320655822753906, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1259087324142456, "min": 0.12222078442573547, "max": 3.0324459075927734, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 277.7156862745098, "min": 259.29824561403507, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28327.0, "min": 15984.0, "max": 32548.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7026666480974824, "min": -1.0000000521540642, "max": 1.7278490412347722, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.6719981059432, "min": -32.000001668930054, "max": 197.9763988852501, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7026666480974824, "min": -1.0000000521540642, "max": 1.7278490412347722, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.6719981059432, "min": -32.000001668930054, "max": 197.9763988852501, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025636872059954376, "min": 0.023871305678863967, "max": 8.689556570723653, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6149609501153463, "min": 2.6040456149348756, "max": 139.03290513157845, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703591636", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703596218" }, "total": 4582.163421858, "count": 1, "self": 0.4897236850001718, "children": { "run_training.setup": { "total": 0.07469269700050063, "count": 1, "self": 0.07469269700050063 }, "TrainerController.start_learning": { "total": 4581.599005476, "count": 1, "self": 2.717112144130624, "children": { "TrainerController._reset_env": { "total": 2.8476325860001452, "count": 1, "self": 2.8476325860001452 }, "TrainerController.advance": { "total": 4575.95170607787, "count": 128676, "self": 2.686522728251475, "children": { "env_step": { "total": 3323.0154406168085, "count": 128676, "self": 3072.895367037817, "children": { "SubprocessEnvManager._take_step": { "total": 248.50247528900218, "count": 128676, "self": 9.002517534170693, "children": { "TorchPolicy.evaluate": { "total": 239.49995775483148, "count": 125057, "self": 239.49995775483148 } } }, "workers": { "total": 1.6175982899894734, "count": 128676, "self": 0.0, "children": { "worker_root": { "total": 4571.89131251693, "count": 128676, "is_parallel": true, "self": 1731.7694439461611, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021878400002606213, "count": 1, "is_parallel": true, "self": 0.0006004870001561358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015873530001044855, "count": 8, "is_parallel": true, "self": 0.0015873530001044855 } } }, "UnityEnvironment.step": { "total": 0.05059555099978752, "count": 1, "is_parallel": true, "self": 0.0005961440001556184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043940500017924933, "count": 1, "is_parallel": true, "self": 0.00043940500017924933 }, "communicator.exchange": { "total": 0.047867543999927875, "count": 1, "is_parallel": true, "self": 0.047867543999927875 }, "steps_from_proto": { "total": 0.0016924579995247768, "count": 1, "is_parallel": true, "self": 0.00034085299921571277, "children": { "_process_rank_one_or_two_observation": { "total": 0.001351605000309064, "count": 8, "is_parallel": true, "self": 0.001351605000309064 } } } } } } }, "UnityEnvironment.step": { "total": 2840.121868570769, "count": 128675, "is_parallel": true, "self": 69.52852001296651, "children": { "UnityEnvironment._generate_step_input": { "total": 47.233149773837795, "count": 128675, "is_parallel": true, "self": 47.233149773837795 }, "communicator.exchange": { "total": 2528.757912858927, "count": 128675, "is_parallel": true, "self": 2528.757912858927 }, "steps_from_proto": { "total": 194.6022859250379, "count": 128675, "is_parallel": true, "self": 37.94970123195617, "children": { "_process_rank_one_or_two_observation": { "total": 156.65258469308174, "count": 1029400, "is_parallel": true, "self": 156.65258469308174 } } } } } } } } } } }, "trainer_advance": { "total": 1250.2497427328099, "count": 128676, "self": 5.257563295713226, "children": { "process_trajectory": { "total": 250.53450240911116, "count": 128676, "self": 250.13637789011227, "children": { "RLTrainer._checkpoint": { "total": 0.398124518998884, "count": 4, "self": 0.398124518998884 } } }, "_update_policy": { "total": 994.4576770279855, "count": 907, "self": 591.3563758008368, "children": { "TorchPPOOptimizer.update": { "total": 403.1013012271487, "count": 45660, "self": 403.1013012271487 } } } } } } }, "trainer_threads": { "total": 8.529987098881975e-07, "count": 1, "self": 8.529987098881975e-07 }, "TrainerController._save_models": { "total": 0.0825538150002103, "count": 1, "self": 0.00148822899973311, "children": { "RLTrainer._checkpoint": { "total": 0.0810655860004772, "count": 1, "self": 0.0810655860004772 } } } } } } }