{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34770864248275757, "min": 0.3458324372768402, "max": 1.406516432762146, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10414.5693359375, "min": 10402.6396484375, "max": 42668.08203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6083505749702454, "min": -0.10395916551351547, "max": 0.6821507215499878, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.90475463867188, "min": -24.950199127197266, "max": 199.18801879882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018120277673006058, "min": -0.0002659456804394722, "max": 0.38335803151130676, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.00119686126709, "min": -0.07340100407600403, "max": 90.85585021972656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06795439173168102, "min": 0.06607992385958138, "max": 0.07726860154202313, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9513614842435344, "min": 0.5408802107941619, "max": 1.0577425270457752, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01494305408033099, "min": 0.0005369297252238916, "max": 0.017152907227359043, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20920275712463385, "min": 0.006980086427910591, "max": 0.24856772867211724, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.292476140635715e-06, "min": 7.292476140635715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010209466596890001, "min": 0.00010209466596890001, "max": 0.0036333682888773002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243079285714285, "min": 0.10243079285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340311, "min": 1.3886848, "max": 2.6111227, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025283620642857144, "min": 0.00025283620642857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035397068900000004, "min": 0.0035397068900000004, "max": 0.12113115772999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00997540820389986, "min": 0.00997540820389986, "max": 0.37242788076400757, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1396557092666626, "min": 0.1396557092666626, "max": 2.606995105743408, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 322.42045454545456, "min": 269.280701754386, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28373.0, "min": 15984.0, "max": 33516.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5411749737845226, "min": -1.0000000521540642, "max": 1.7085666515325244, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.623397693038, "min": -29.912201583385468, "max": 194.9837986677885, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5411749737845226, "min": -1.0000000521540642, "max": 1.7085666515325244, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.623397693038, "min": -29.912201583385468, "max": 194.9837986677885, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03346216039352095, "min": 0.029686047477424954, "max": 7.400478691793978, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9446701146298437, "min": 2.9446701146298437, "max": 118.40765906870365, "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": "1682343613", "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": "1682345867" }, "total": 2254.49466957, "count": 1, "self": 0.48308647599969845, "children": { "run_training.setup": { "total": 0.10567973299998812, "count": 1, "self": 0.10567973299998812 }, "TrainerController.start_learning": { "total": 2253.905903361, "count": 1, "self": 1.4818276949649771, "children": { "TrainerController._reset_env": { "total": 4.878646647000096, "count": 1, "self": 4.878646647000096 }, "TrainerController.advance": { "total": 2247.4505638970345, "count": 64092, "self": 1.531320670072546, "children": { "env_step": { "total": 1627.2636931759353, "count": 64092, "self": 1515.3714760799758, "children": { "SubprocessEnvManager._take_step": { "total": 110.97595803696413, "count": 64092, "self": 4.780674568906534, "children": { "TorchPolicy.evaluate": { "total": 106.1952834680576, "count": 62551, "self": 106.1952834680576 } } }, "workers": { "total": 0.9162590589953652, "count": 64092, "self": 0.0, "children": { "worker_root": { "total": 2248.5514060860123, "count": 64092, "is_parallel": true, "self": 848.4623180150236, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017303800000263436, "count": 1, "is_parallel": true, "self": 0.0005010040001707239, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012293759998556197, "count": 8, "is_parallel": true, "self": 0.0012293759998556197 } } }, "UnityEnvironment.step": { "total": 0.08145376800007398, "count": 1, "is_parallel": true, "self": 0.0005276630004118488, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004525939998529793, "count": 1, "is_parallel": true, "self": 0.0004525939998529793 }, "communicator.exchange": { "total": 0.07892114699984631, "count": 1, "is_parallel": true, "self": 0.07892114699984631 }, "steps_from_proto": { "total": 0.0015523639999628358, "count": 1, "is_parallel": true, "self": 0.0003574119996301306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011949520003327052, "count": 8, "is_parallel": true, "self": 0.0011949520003327052 } } } } } } }, "UnityEnvironment.step": { "total": 1400.0890880709887, "count": 64091, "is_parallel": true, "self": 33.080038759916306, "children": { "UnityEnvironment._generate_step_input": { "total": 22.936065203089584, "count": 64091, "is_parallel": true, "self": 22.936065203089584 }, "communicator.exchange": { "total": 1248.3813406220124, "count": 64091, "is_parallel": true, "self": 1248.3813406220124 }, "steps_from_proto": { "total": 95.69164348597042, "count": 64091, "is_parallel": true, "self": 20.487145899953248, "children": { "_process_rank_one_or_two_observation": { "total": 75.20449758601717, "count": 512728, "is_parallel": true, "self": 75.20449758601717 } } } } } } } } } } }, "trainer_advance": { "total": 618.6555500510265, "count": 64092, "self": 2.833213958053193, "children": { "process_trajectory": { "total": 106.92304268797147, "count": 64092, "self": 106.72024806997183, "children": { "RLTrainer._checkpoint": { "total": 0.20279461799964338, "count": 2, "self": 0.20279461799964338 } } }, "_update_policy": { "total": 508.8992934050018, "count": 455, "self": 322.3112727669686, "children": { "TorchPPOOptimizer.update": { "total": 186.58802063803319, "count": 22833, "self": 186.58802063803319 } } } } } } }, "trainer_threads": { "total": 1.0370004019932821e-06, "count": 1, "self": 1.0370004019932821e-06 }, "TrainerController._save_models": { "total": 0.09486408500015386, "count": 1, "self": 0.0015450270002475008, "children": { "RLTrainer._checkpoint": { "total": 0.09331905799990636, "count": 1, "self": 0.09331905799990636 } } } } } } }