{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5425063967704773, "min": 0.5270963907241821, "max": 1.413527488708496, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16205.751953125, "min": 15644.220703125, "max": 42880.76953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3304080367088318, "min": -0.14370810985565186, "max": 0.33562496304512024, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.58445739746094, "min": -34.05882263183594, "max": 86.59123992919922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.14816218614578247, "min": -0.22038647532463074, "max": 0.741780698299408, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 37.92951965332031, "min": -56.859710693359375, "max": 175.80203247070312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06621870913178235, "min": 0.0648226594926053, "max": 0.0721828293223705, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9270619278449529, "min": 0.5006122238202764, "max": 1.0149849092213472, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013899843539372089, "min": 0.0009848378842930207, "max": 0.019601497236902198, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19459780955120926, "min": 0.011818054611516249, "max": 0.23520615516948357, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.54014748665e-06, "min": 7.54014748665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001055620648131, "min": 0.0001055620648131, "max": 0.0032562257145914994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251335000000002, "min": 0.10251335000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351869000000002, "min": 1.3886848, "max": 2.4006906999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261083665, "min": 0.000261083665, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00365517131, "min": 0.00365517131, "max": 0.10856230915000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011282798834145069, "min": 0.011282798834145069, "max": 0.8014407753944397, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15795917809009552, "min": 0.15795917809009552, "max": 5.610085487365723, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 553.6785714285714, "min": 482.1, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31006.0, "min": 15984.0, "max": 35040.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1605142558525716, "min": -1.0000000521540642, "max": 1.3506950517414047, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.98879832774401, "min": -29.8090016618371, "max": 82.39239815622568, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1605142558525716, "min": -1.0000000521540642, "max": 1.3506950517414047, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.98879832774401, "min": -29.8090016618371, "max": 82.39239815622568, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06510442841174933, "min": 0.058035823600519384, "max": 16.753343254327774, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6458479910579626, "min": 3.3902062239067163, "max": 268.0534920692444, "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": "1697636455", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697638579" }, "total": 2123.728369077, "count": 1, "self": 0.47568564300036087, "children": { "run_training.setup": { "total": 0.04338381999991725, "count": 1, "self": 0.04338381999991725 }, "TrainerController.start_learning": { "total": 2123.209299614, "count": 1, "self": 1.3452846249256254, "children": { "TrainerController._reset_env": { "total": 3.042549364000024, "count": 1, "self": 3.042549364000024 }, "TrainerController.advance": { "total": 2118.7452615240745, "count": 63435, "self": 1.3890371830834738, "children": { "env_step": { "total": 1508.586103113992, "count": 63435, "self": 1385.400330533904, "children": { "SubprocessEnvManager._take_step": { "total": 122.37893506408227, "count": 63435, "self": 4.543668387069829, "children": { "TorchPolicy.evaluate": { "total": 117.83526667701244, "count": 62572, "self": 117.83526667701244 } } }, "workers": { "total": 0.8068375160057712, "count": 63435, "self": 0.0, "children": { "worker_root": { "total": 2118.6662928169944, "count": 63435, "is_parallel": true, "self": 846.7371872440226, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017083019999972748, "count": 1, "is_parallel": true, "self": 0.0005239869997240021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011843150002732727, "count": 8, "is_parallel": true, "self": 0.0011843150002732727 } } }, "UnityEnvironment.step": { "total": 0.10526572000003398, "count": 1, "is_parallel": true, "self": 0.0005666860001838359, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004555220000383997, "count": 1, "is_parallel": true, "self": 0.0004555220000383997 }, "communicator.exchange": { "total": 0.10258392299988373, "count": 1, "is_parallel": true, "self": 0.10258392299988373 }, "steps_from_proto": { "total": 0.001659588999928019, "count": 1, "is_parallel": true, "self": 0.00040071000034913595, "children": { "_process_rank_one_or_two_observation": { "total": 0.001258878999578883, "count": 8, "is_parallel": true, "self": 0.001258878999578883 } } } } } } }, "UnityEnvironment.step": { "total": 1271.9291055729718, "count": 63434, "is_parallel": true, "self": 33.978409333879426, "children": { "UnityEnvironment._generate_step_input": { "total": 23.82013983698107, "count": 63434, "is_parallel": true, "self": 23.82013983698107 }, "communicator.exchange": { "total": 1118.0067510050155, "count": 63434, "is_parallel": true, "self": 1118.0067510050155 }, "steps_from_proto": { "total": 96.1238053970958, "count": 63434, "is_parallel": true, "self": 18.905551253132444, "children": { "_process_rank_one_or_two_observation": { "total": 77.21825414396335, "count": 507472, "is_parallel": true, "self": 77.21825414396335 } } } } } } } } } } }, "trainer_advance": { "total": 608.770121226999, "count": 63435, "self": 2.4759001920442643, "children": { "process_trajectory": { "total": 115.64375175396003, "count": 63435, "self": 115.46989586395989, "children": { "RLTrainer._checkpoint": { "total": 0.1738558900001408, "count": 2, "self": 0.1738558900001408 } } }, "_update_policy": { "total": 490.6504692809947, "count": 444, "self": 293.8579451389926, "children": { "TorchPPOOptimizer.update": { "total": 196.7925241420021, "count": 22803, "self": 196.7925241420021 } } } } } } }, "trainer_threads": { "total": 1.0839999049494509e-06, "count": 1, "self": 1.0839999049494509e-06 }, "TrainerController._save_models": { "total": 0.07620301699989795, "count": 1, "self": 0.001395037999827764, "children": { "RLTrainer._checkpoint": { "total": 0.07480797900007019, "count": 1, "self": 0.07480797900007019 } } } } } } }