{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46644073724746704, "min": 0.46160316467285156, "max": 1.4436880350112915, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14030.537109375, "min": 13899.794921875, "max": 43795.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5171449780464172, "min": -0.10591541975736618, "max": 0.5597642660140991, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.283447265625, "min": -25.419700622558594, "max": 156.17422485351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.39252832531929016, "min": -0.39252832531929016, "max": 0.38804349303245544, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -109.5154037475586, "min": -109.5154037475586, "max": 91.96630859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06783523745576127, "min": 0.06333998555921773, "max": 0.07367470096575009, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.017528561836419, "min": 0.5157229067602506, "max": 1.066549697687151, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02624574820769744, "min": 0.00016575283295504442, "max": 0.027949749393710154, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3936862231154616, "min": 0.0021547868284155776, "max": 0.3936862231154616, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.517697494133338e-06, "min": 7.517697494133338e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011276546241200007, "min": 0.00011276546241200007, "max": 0.0032601107132964996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250586666666668, "min": 0.10250586666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375880000000002, "min": 1.3886848, "max": 2.4004693, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603360800000002, "min": 0.0002603360800000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039050412000000024, "min": 0.0039050412000000024, "max": 0.10869167965000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009919160977005959, "min": 0.009919160977005959, "max": 0.5105599164962769, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14878740906715393, "min": 0.1453237384557724, "max": 3.5739192962646484, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.01075268817203, "min": 324.65909090909093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31993.0, "min": 15984.0, "max": 32863.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.548432237118162, "min": -1.0000000521540642, "max": 1.6071408910846168, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.00419805198908, "min": -31.99760165810585, "max": 144.71459794044495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.548432237118162, "min": -1.0000000521540642, "max": 1.6071408910846168, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.00419805198908, "min": -31.99760165810585, "max": 144.71459794044495, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03552449587012781, "min": 0.03481376057144106, "max": 11.238712195307016, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3037781159218866, "min": 3.0636109302868135, "max": 179.81939512491226, "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": "1784479792", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/shamik/anaconda3/envs/rl-env-py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1784480591" }, "total": 798.5821962400005, "count": 1, "self": 0.21738799100057804, "children": { "run_training.setup": { "total": 0.01649790299779852, "count": 1, "self": 0.01649790299779852 }, "TrainerController.start_learning": { "total": 798.3483103460021, "count": 1, "self": 0.7739746934348659, "children": { "TrainerController._reset_env": { "total": 1.583553145002952, "count": 1, "self": 1.583553145002952 }, "TrainerController.advance": { "total": 795.9471079975629, "count": 63805, "self": 0.7824412176305486, "children": { "env_step": { "total": 520.7543771082019, "count": 63805, "self": 436.171200762783, "children": { "SubprocessEnvManager._take_step": { "total": 84.07094967138255, "count": 63805, "self": 2.4220798048190773, "children": { "TorchPolicy.evaluate": { "total": 81.64886986656347, "count": 62550, "self": 81.64886986656347 } } }, "workers": { "total": 0.5122266740363557, "count": 63805, "self": 0.0, "children": { "worker_root": { "total": 797.315431848856, "count": 63805, "is_parallel": true, "self": 409.33571129366464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007795780002197716, "count": 1, "is_parallel": true, "self": 0.00022881800032337196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005507599998963997, "count": 8, "is_parallel": true, "self": 0.0005507599998963997 } } }, "UnityEnvironment.step": { "total": 0.019008727998880204, "count": 1, "is_parallel": true, "self": 0.0002116309988196008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013867999950889498, "count": 1, "is_parallel": true, "self": 0.00013867999950889498 }, "communicator.exchange": { "total": 0.01780818800034467, "count": 1, "is_parallel": true, "self": 0.01780818800034467 }, "steps_from_proto": { "total": 0.0008502290002070367, "count": 1, "is_parallel": true, "self": 0.00020014600158901885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006500829986180179, "count": 8, "is_parallel": true, "self": 0.0006500829986180179 } } } } } } }, "UnityEnvironment.step": { "total": 387.9797205551913, "count": 63804, "is_parallel": true, "self": 10.688087126036407, "children": { "UnityEnvironment._generate_step_input": { "total": 6.811728802942525, "count": 63804, "is_parallel": true, "self": 6.811728802942525 }, "communicator.exchange": { "total": 341.58526991112376, "count": 63804, "is_parallel": true, "self": 341.58526991112376 }, "steps_from_proto": { "total": 28.894634715088614, "count": 63804, "is_parallel": true, "self": 6.44946645044547, "children": { "_process_rank_one_or_two_observation": { "total": 22.445168264643144, "count": 510432, "is_parallel": true, "self": 22.445168264643144 } } } } } } } } } } }, "trainer_advance": { "total": 274.4102896717304, "count": 63805, "self": 1.311965420776687, "children": { "process_trajectory": { "total": 53.214320514955034, "count": 63805, "self": 53.065851937953994, "children": { "RLTrainer._checkpoint": { "total": 0.1484685770010401, "count": 2, "self": 0.1484685770010401 } } }, "_update_policy": { "total": 219.8840037359987, "count": 444, "self": 115.40770527983113, "children": { "TorchPPOOptimizer.update": { "total": 104.47629845616757, "count": 22809, "self": 104.47629845616757 } } } } } } }, "trainer_threads": { "total": 4.780013114213943e-07, "count": 1, "self": 4.780013114213943e-07 }, "TrainerController._save_models": { "total": 0.04367403200012632, "count": 1, "self": 0.0004935439974360634, "children": { "RLTrainer._checkpoint": { "total": 0.043180488002690254, "count": 1, "self": 0.043180488002690254 } } } } } } }