{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5584539175033569, "min": 0.5424883365631104, "max": 1.5432878732681274, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16771.48828125, "min": 16239.931640625, "max": 46817.1796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46928051114082336, "min": -0.11491169035434723, "max": 0.46928051114082336, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.05213928222656, "min": -27.69371795654297, "max": 129.05213928222656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012036911211907864, "min": -0.011820772662758827, "max": 0.1460367739200592, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.310150623321533, "min": -3.0497593879699707, "max": 35.048824310302734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06977593196099115, "min": 0.0655878812952423, "max": 0.07439832252126477, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9768630474538761, "min": 0.4996375243613382, "max": 1.054324863096197, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012675950944844581, "min": 7.200862915770852e-05, "max": 0.013439109137877547, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17746331322782413, "min": 0.0009361121790502109, "max": 0.2015866370681632, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.299847566750001e-06, "min": 7.299847566750001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010219786593450002, "min": 0.00010219786593450002, "max": 0.0035071916309361998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243325000000002, "min": 0.10243325000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340655000000002, "min": 1.3886848, "max": 2.5690638, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025308167500000007, "min": 0.00025308167500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003543143450000001, "min": 0.003543143450000001, "max": 0.11692947362, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009155969135463238, "min": 0.009155969135463238, "max": 0.2529488801956177, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12818357348442078, "min": 0.12818357348442078, "max": 1.7706421613693237, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 416.9230769230769, "min": 416.9230769230769, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32520.0, "min": 15984.0, "max": 32576.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4548358879028223, "min": -1.0000000521540642, "max": 1.4751790885382623, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.47719925642014, "min": -31.998801663517952, "max": 113.47719925642014, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4548358879028223, "min": -1.0000000521540642, "max": 1.4751790885382623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.47719925642014, "min": -31.998801663517952, "max": 113.47719925642014, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03988702849108869, "min": 0.03988702849108869, "max": 5.240349592640996, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.111188222304918, "min": 2.8574442435638048, "max": 83.84559348225594, "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": "1698793663", "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 --force", "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": "1698795801" }, "total": 2137.3757730139996, "count": 1, "self": 0.48059727599957114, "children": { "run_training.setup": { "total": 0.043499555999915174, "count": 1, "self": 0.043499555999915174 }, "TrainerController.start_learning": { "total": 2136.851676182, "count": 1, "self": 1.6691046750711394, "children": { "TrainerController._reset_env": { "total": 3.4747453049994874, "count": 1, "self": 3.4747453049994874 }, "TrainerController.advance": { "total": 2131.6275181089295, "count": 63437, "self": 1.6761905979319636, "children": { "env_step": { "total": 1493.6751518709661, "count": 63437, "self": 1345.5621009008728, "children": { "SubprocessEnvManager._take_step": { "total": 147.0924882639374, "count": 63437, "self": 4.905375114922208, "children": { "TorchPolicy.evaluate": { "total": 142.1871131490152, "count": 62568, "self": 142.1871131490152 } } }, "workers": { "total": 1.0205627061559426, "count": 63437, "self": 0.0, "children": { "worker_root": { "total": 2131.669354081915, "count": 63437, "is_parallel": true, "self": 912.1841527410079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019428349996815086, "count": 1, "is_parallel": true, "self": 0.0006240150005396572, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013188199991418514, "count": 8, "is_parallel": true, "self": 0.0013188199991418514 } } }, "UnityEnvironment.step": { "total": 0.08535198000026867, "count": 1, "is_parallel": true, "self": 0.0006180660011523287, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004901849997622776, "count": 1, "is_parallel": true, "self": 0.0004901849997622776 }, "communicator.exchange": { "total": 0.08256691599945043, "count": 1, "is_parallel": true, "self": 0.08256691599945043 }, "steps_from_proto": { "total": 0.0016768129999036319, "count": 1, "is_parallel": true, "self": 0.0003444159983700956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013323970015335362, "count": 8, "is_parallel": true, "self": 0.0013323970015335362 } } } } } } }, "UnityEnvironment.step": { "total": 1219.4852013409072, "count": 63436, "is_parallel": true, "self": 36.01234889411717, "children": { "UnityEnvironment._generate_step_input": { "total": 25.926297319037076, "count": 63436, "is_parallel": true, "self": 25.926297319037076 }, "communicator.exchange": { "total": 1051.4988286948173, "count": 63436, "is_parallel": true, "self": 1051.4988286948173 }, "steps_from_proto": { "total": 106.04772643293563, "count": 63436, "is_parallel": true, "self": 22.022004538846886, "children": { "_process_rank_one_or_two_observation": { "total": 84.02572189408875, "count": 507488, "is_parallel": true, "self": 84.02572189408875 } } } } } } } } } } }, "trainer_advance": { "total": 636.2761756400314, "count": 63437, "self": 2.9647774109507736, "children": { "process_trajectory": { "total": 124.24613849808338, "count": 63437, "self": 124.02727809308271, "children": { "RLTrainer._checkpoint": { "total": 0.21886040500066883, "count": 2, "self": 0.21886040500066883 } } }, "_update_policy": { "total": 509.06525973099724, "count": 446, "self": 300.4494868020329, "children": { "TorchPPOOptimizer.update": { "total": 208.61577292896436, "count": 22869, "self": 208.61577292896436 } } } } } } }, "trainer_threads": { "total": 1.1399997674743645e-06, "count": 1, "self": 1.1399997674743645e-06 }, "TrainerController._save_models": { "total": 0.08030695300021762, "count": 1, "self": 0.002078958000311104, "children": { "RLTrainer._checkpoint": { "total": 0.07822799499990651, "count": 1, "self": 0.07822799499990651 } } } } } } }