{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45040199160575867, "min": 0.44834181666374207, "max": 1.4811451435089111, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13418.3759765625, "min": 13418.3759765625, "max": 44932.01953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4475919008255005, "min": -0.20256419479846954, "max": 0.4969637393951416, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.4022216796875, "min": -48.007713317871094, "max": 135.17413330078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.760097324848175, "min": -0.8235419988632202, "max": 0.22838452458381653, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -204.4661865234375, "min": -224.00341796875, "max": 54.812286376953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0680208614919268, "min": 0.06231259228176592, "max": 0.0738108723217333, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9522920608869754, "min": 0.4994454979378029, "max": 1.0515792563645507, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.05130720258014099, "min": 0.00032291116593113526, "max": 0.06541723518014242, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7183008361219738, "min": 0.004520756323035894, "max": 0.9158412925219939, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.64309030947857e-06, "min": 7.64309030947857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001070032643327, "min": 0.0001070032643327, "max": 0.0034924522358492998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254766428571428, "min": 0.10254766428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356673, "min": 1.3886848, "max": 2.5277033999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026451166214285713, "min": 0.00026451166214285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037031632699999996, "min": 0.0037031632699999996, "max": 0.11642865492999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013095549307763577, "min": 0.012328043580055237, "max": 0.372881680727005, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18333768844604492, "min": 0.17259261012077332, "max": 2.6101717948913574, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 379.06493506493507, "min": 379.06493506493507, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29188.0, "min": 15984.0, "max": 33371.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.491041529488254, "min": -1.0000000521540642, "max": 1.568435874600441, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.81019777059555, "min": -30.48560168594122, "max": 122.3379982188344, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.491041529488254, "min": -1.0000000521540642, "max": 1.568435874600441, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.81019777059555, "min": -30.48560168594122, "max": 122.3379982188344, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05195024093407412, "min": 0.05195024093407412, "max": 7.096920130774379, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.000168551923707, "min": 3.3936313287122175, "max": 113.55072209239006, "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": "1713757823", "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": "1713759790" }, "total": 1967.325133059, "count": 1, "self": 0.5262686219994066, "children": { "run_training.setup": { "total": 0.04908654300015769, "count": 1, "self": 0.04908654300015769 }, "TrainerController.start_learning": { "total": 1966.7497778940005, "count": 1, "self": 1.2117644400887002, "children": { "TrainerController._reset_env": { "total": 2.727127002999623, "count": 1, "self": 2.727127002999623 }, "TrainerController.advance": { "total": 1962.7241642589124, "count": 63606, "self": 1.2408176917624587, "children": { "env_step": { "total": 1362.647079312108, "count": 63606, "self": 1239.0892114392236, "children": { "SubprocessEnvManager._take_step": { "total": 122.79282919988418, "count": 63606, "self": 4.254844589988352, "children": { "TorchPolicy.evaluate": { "total": 118.53798460989583, "count": 62554, "self": 118.53798460989583 } } }, "workers": { "total": 0.7650386730001628, "count": 63606, "self": 0.0, "children": { "worker_root": { "total": 1962.5317188630088, "count": 63606, "is_parallel": true, "self": 832.7685842099891, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002545997999732208, "count": 1, "is_parallel": true, "self": 0.0006860170005893451, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018599809991428629, "count": 8, "is_parallel": true, "self": 0.0018599809991428629 } } }, "UnityEnvironment.step": { "total": 0.04827534400010336, "count": 1, "is_parallel": true, "self": 0.0006860440007585566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004521569999269559, "count": 1, "is_parallel": true, "self": 0.0004521569999269559 }, "communicator.exchange": { "total": 0.04527436199987278, "count": 1, "is_parallel": true, "self": 0.04527436199987278 }, "steps_from_proto": { "total": 0.0018627809995450662, "count": 1, "is_parallel": true, "self": 0.0004203249982310808, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014424560013139853, "count": 8, "is_parallel": true, "self": 0.0014424560013139853 } } } } } } }, "UnityEnvironment.step": { "total": 1129.7631346530197, "count": 63605, "is_parallel": true, "self": 32.912526846152105, "children": { "UnityEnvironment._generate_step_input": { "total": 22.55713449005634, "count": 63605, "is_parallel": true, "self": 22.55713449005634 }, "communicator.exchange": { "total": 980.1861377870682, "count": 63605, "is_parallel": true, "self": 980.1861377870682 }, "steps_from_proto": { "total": 94.10733552974307, "count": 63605, "is_parallel": true, "self": 18.33783173885513, "children": { "_process_rank_one_or_two_observation": { "total": 75.76950379088794, "count": 508840, "is_parallel": true, "self": 75.76950379088794 } } } } } } } } } } }, "trainer_advance": { "total": 598.836267255042, "count": 63606, "self": 2.424546589084457, "children": { "process_trajectory": { "total": 119.76258868494915, "count": 63606, "self": 119.36867942694971, "children": { "RLTrainer._checkpoint": { "total": 0.39390925799943943, "count": 2, "self": 0.39390925799943943 } } }, "_update_policy": { "total": 476.6491319810084, "count": 452, "self": 275.82213764603875, "children": { "TorchPPOOptimizer.update": { "total": 200.82699433496964, "count": 22773, "self": 200.82699433496964 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.08672129699971265, "count": 1, "self": 0.0013666209997609258, "children": { "RLTrainer._checkpoint": { "total": 0.08535467599995172, "count": 1, "self": 0.08535467599995172 } } } } } } }