{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3817181885242462, "min": 0.3817181885242462, "max": 1.462928295135498, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11439.3310546875, "min": 11439.3310546875, "max": 44379.39453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989876.0, "min": 29952.0, "max": 989876.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989876.0, "min": 29952.0, "max": 989876.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4439846873283386, "min": -0.12145934253931046, "max": 0.5775772929191589, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.431884765625, "min": -29.39316177368164, "max": 163.78372192382812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03619305416941643, "min": -0.1592051237821579, "max": 0.30137020349502563, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.735931396484375, "min": -41.234127044677734, "max": 72.63021850585938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07062915362338132, "min": 0.06570433203006057, "max": 0.07565576343783574, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9888081507273385, "min": 0.5295903440648502, "max": 1.0503451101637133, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014783945759744984, "min": 0.0001980511182137315, "max": 0.019633743017782698, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20697524063642977, "min": 0.0025746645367785096, "max": 0.27487240224895776, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.731847422750003e-06, "min": 7.731847422750003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010824586391850004, "min": 0.00010824586391850004, "max": 0.0033756358747880993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257725, "min": 0.10257725, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360815, "min": 1.3886848, "max": 2.4252119, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002674672750000001, "min": 0.0002674672750000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003744541850000002, "min": 0.003744541850000002, "max": 0.11253866880999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013486322946846485, "min": 0.013486322946846485, "max": 0.46075740456581116, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18880851566791534, "min": 0.18880851566791534, "max": 3.225301742553711, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.75, "min": 306.8333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31445.0, "min": 15984.0, "max": 32967.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4283078695206266, "min": -1.0000000521540642, "max": 1.6723270535779495, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.55139808356762, "min": -31.996801659464836, "max": 160.54339714348316, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4283078695206266, "min": -1.0000000521540642, "max": 1.6723270535779495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.55139808356762, "min": -31.996801659464836, "max": 160.54339714348316, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.057614636967053615, "min": 0.04991505024408531, "max": 8.629222057759762, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.3787124094960745, "min": 4.04311906977091, "max": 138.0675529241562, "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": "1760237507", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/environment/miniconda3/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --force --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": "1760239409" }, "total": 1902.4375437229999, "count": 1, "self": 0.4246169799996551, "children": { "run_training.setup": { "total": 0.04659206099995572, "count": 1, "self": 0.04659206099995572 }, "TrainerController.start_learning": { "total": 1901.9663346820003, "count": 1, "self": 0.9665804918834056, "children": { "TrainerController._reset_env": { "total": 4.8143533979998665, "count": 1, "self": 4.8143533979998665 }, "TrainerController.advance": { "total": 1896.116772749117, "count": 63728, "self": 0.9136694141129738, "children": { "env_step": { "total": 1233.4892155770913, "count": 63728, "self": 1112.3540708930914, "children": { "SubprocessEnvManager._take_step": { "total": 120.57224166997207, "count": 63728, "self": 3.502090220021273, "children": { "TorchPolicy.evaluate": { "total": 117.0701514499508, "count": 62578, "self": 117.0701514499508 } } }, "workers": { "total": 0.5629030140278246, "count": 63728, "self": 0.0, "children": { "worker_root": { "total": 1899.2138721169583, "count": 63728, "is_parallel": true, "self": 881.5417636209695, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004729730999997628, "count": 1, "is_parallel": true, "self": 0.0013939090003987076, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033358219995989202, "count": 8, "is_parallel": true, "self": 0.0033358219995989202 } } }, "UnityEnvironment.step": { "total": 0.0488378110001122, "count": 1, "is_parallel": true, "self": 0.0006207230003383302, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007245739998325007, "count": 1, "is_parallel": true, "self": 0.0007245739998325007 }, "communicator.exchange": { "total": 0.045769815000085146, "count": 1, "is_parallel": true, "self": 0.045769815000085146 }, "steps_from_proto": { "total": 0.0017226989998562203, "count": 1, "is_parallel": true, "self": 0.00036063399988961464, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013620649999666057, "count": 8, "is_parallel": true, "self": 0.0013620649999666057 } } } } } } }, "UnityEnvironment.step": { "total": 1017.6721084959888, "count": 63727, "is_parallel": true, "self": 23.625297090090044, "children": { "UnityEnvironment._generate_step_input": { "total": 16.37866502396423, "count": 63727, "is_parallel": true, "self": 16.37866502396423 }, "communicator.exchange": { "total": 915.8770471409582, "count": 63727, "is_parallel": true, "self": 915.8770471409582 }, "steps_from_proto": { "total": 61.79109924097634, "count": 63727, "is_parallel": true, "self": 13.113283899825092, "children": { "_process_rank_one_or_two_observation": { "total": 48.677815341151245, "count": 509816, "is_parallel": true, "self": 48.677815341151245 } } } } } } } } } } }, "trainer_advance": { "total": 661.7138877579127, "count": 63728, "self": 1.9668749539428063, "children": { "process_trajectory": { "total": 111.19098275696683, "count": 63728, "self": 111.00955135396703, "children": { "RLTrainer._checkpoint": { "total": 0.18143140299980587, "count": 2, "self": 0.18143140299980587 } } }, "_update_policy": { "total": 548.5560300470031, "count": 445, "self": 264.2065940489824, "children": { "TorchPPOOptimizer.update": { "total": 284.3494359980207, "count": 22857, "self": 284.3494359980207 } } } } } } }, "trainer_threads": { "total": 9.800000952964183e-07, "count": 1, "self": 9.800000952964183e-07 }, "TrainerController._save_models": { "total": 0.0686270629998944, "count": 1, "self": 0.001995081000131904, "children": { "RLTrainer._checkpoint": { "total": 0.0666319819997625, "count": 1, "self": 0.0666319819997625 } } } } } } }