{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4243793487548828, "min": 0.4199554920196533, "max": 1.4434819221496582, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12853.6015625, "min": 12531.4716796875, "max": 43789.46875, "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": 0.4187171161174774, "min": -0.11975310742855072, "max": 0.42197513580322266, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.12260437011719, "min": -28.860498428344727, "max": 111.82341003417969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.4220917522907257, "min": -0.4220917522907257, "max": 0.31527772545814514, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -111.0101318359375, "min": -111.0101318359375, "max": 75.66665649414062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06906399833238507, "min": 0.06493967401194099, "max": 0.07620442352974748, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.966895976653391, "min": 0.48231874653904283, "max": 1.0668619294164647, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.029551414293592475, "min": 0.0005479941266479391, "max": 0.029551414293592475, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.41371980011029463, "min": 0.004976144313185687, "max": 0.41371980011029463, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.41682609918571e-06, "min": 7.41682609918571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010383556538859994, "min": 0.00010383556538859994, "max": 0.0033827675724108996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247224285714285, "min": 0.10247224285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346113999999999, "min": 1.3691136000000002, "max": 2.5275891, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002569770614285713, "min": 0.0002569770614285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035976788599999983, "min": 0.0035976788599999983, "max": 0.11278615109000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010249814949929714, "min": 0.010249814949929714, "max": 0.5477643609046936, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14349740743637085, "min": 0.14349740743637085, "max": 3.8343505859375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.14285714285717, "min": 429.9142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28296.0, "min": 15984.0, "max": 33478.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3920698125684072, "min": -1.0000000521540642, "max": 1.456515472434776, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.70039819180965, "min": -32.000001668930054, "max": 103.41259854286909, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3920698125684072, "min": -1.0000000521540642, "max": 1.456515472434776, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.70039819180965, "min": -32.000001668930054, "max": 103.41259854286909, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047398575511391434, "min": 0.047311737468826574, "max": 11.649056665599346, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9861102572176605, "min": 2.9861102572176605, "max": 186.38490664958954, "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": "1698519451", "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 --force --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698521539" }, "total": 2087.875699298, "count": 1, "self": 0.48773208400007206, "children": { "run_training.setup": { "total": 0.07018652900001143, "count": 1, "self": 0.07018652900001143 }, "TrainerController.start_learning": { "total": 2087.317780685, "count": 1, "self": 1.327939576978224, "children": { "TrainerController._reset_env": { "total": 3.559111456999972, "count": 1, "self": 3.559111456999972 }, "TrainerController.advance": { "total": 2082.3513247560218, "count": 63528, "self": 1.4231148380790728, "children": { "env_step": { "total": 1462.3772034229544, "count": 63528, "self": 1331.6456673488499, "children": { "SubprocessEnvManager._take_step": { "total": 129.9240065101037, "count": 63528, "self": 4.49307444212036, "children": { "TorchPolicy.evaluate": { "total": 125.43093206798335, "count": 62566, "self": 125.43093206798335 } } }, "workers": { "total": 0.807529564000788, "count": 63528, "self": 0.0, "children": { "worker_root": { "total": 2082.823332214973, "count": 63528, "is_parallel": true, "self": 866.7665591889618, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005852454999967449, "count": 1, "is_parallel": true, "self": 0.0008678989995587472, "children": { "_process_rank_one_or_two_observation": { "total": 0.004984556000408702, "count": 8, "is_parallel": true, "self": 0.004984556000408702 } } }, "UnityEnvironment.step": { "total": 0.04979792700009966, "count": 1, "is_parallel": true, "self": 0.0005714090000310534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005057670000496728, "count": 1, "is_parallel": true, "self": 0.0005057670000496728 }, "communicator.exchange": { "total": 0.04693084099994849, "count": 1, "is_parallel": true, "self": 0.04693084099994849 }, "steps_from_proto": { "total": 0.0017899100000704493, "count": 1, "is_parallel": true, "self": 0.00038808200042694807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014018279996435012, "count": 8, "is_parallel": true, "self": 0.0014018279996435012 } } } } } } }, "UnityEnvironment.step": { "total": 1216.0567730260113, "count": 63527, "is_parallel": true, "self": 34.32514730208959, "children": { "UnityEnvironment._generate_step_input": { "total": 25.77183916695185, "count": 63527, "is_parallel": true, "self": 25.77183916695185 }, "communicator.exchange": { "total": 1055.4508216550507, "count": 63527, "is_parallel": true, "self": 1055.4508216550507 }, "steps_from_proto": { "total": 100.50896490191917, "count": 63527, "is_parallel": true, "self": 20.405501439744512, "children": { "_process_rank_one_or_two_observation": { "total": 80.10346346217466, "count": 508216, "is_parallel": true, "self": 80.10346346217466 } } } } } } } } } } }, "trainer_advance": { "total": 618.5510064949885, "count": 63528, "self": 2.5666492829993786, "children": { "process_trajectory": { "total": 121.91509876199302, "count": 63528, "self": 121.7022575799931, "children": { "RLTrainer._checkpoint": { "total": 0.21284118199992008, "count": 2, "self": 0.21284118199992008 } } }, "_update_policy": { "total": 494.06925844999614, "count": 444, "self": 291.8332331719821, "children": { "TorchPPOOptimizer.update": { "total": 202.23602527801404, "count": 22818, "self": 202.23602527801404 } } } } } } }, "trainer_threads": { "total": 1.008999788609799e-06, "count": 1, "self": 1.008999788609799e-06 }, "TrainerController._save_models": { "total": 0.07940388599990911, "count": 1, "self": 0.0014153229999465111, "children": { "RLTrainer._checkpoint": { "total": 0.0779885629999626, "count": 1, "self": 0.0779885629999626 } } } } } } }