{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3736896216869354, "min": 0.36806291341781616, "max": 1.4841479063034058, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11156.876953125, "min": 11156.876953125, "max": 45023.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29968.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29968.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5215446352958679, "min": -0.11508747935295105, "max": 0.5412690043449402, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.94631958007812, "min": -27.736082077026367, "max": 150.1361846923828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008111745119094849, "min": -0.004144327715039253, "max": 0.2217487394809723, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.2388415336608887, "min": -1.0733808279037476, "max": 53.219696044921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06677421650957546, "min": 0.0644609747978393, "max": 0.07246215414904457, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9348390311340564, "min": 0.5506977347232054, "max": 1.053370826082149, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012013696498092113, "min": 0.0008089976459485291, "max": 0.015579984508804047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1681917509732896, "min": 0.007280978813536762, "max": 0.21811978312325667, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4411475196499935e-06, "min": 7.4411475196499935e-06, "max": 0.0002948526017158, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010417606527509991, "min": 0.00010417606527509991, "max": 0.0035073929308691, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248035000000001, "min": 0.10248035000000001, "max": 0.19828420000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347249000000002, "min": 1.4347249000000002, "max": 2.5723884, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002577869649999998, "min": 0.0002577869649999998, "max": 0.00982859158, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036090175099999975, "min": 0.0036090175099999975, "max": 0.11693617691, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006372568663209677, "min": 0.006236912216991186, "max": 0.3572459816932678, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0892159640789032, "min": 0.0892159640789032, "max": 2.8579678535461426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.11392405063293, "min": 357.2682926829268, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29081.0, "min": 16255.0, "max": 33644.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5306025034264674, "min": -0.999987552408129, "max": 1.6183316874794844, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.91759777069092, "min": -31.999601677060127, "max": 132.91879758238792, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5306025034264674, "min": -0.999987552408129, "max": 1.6183316874794844, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.91759777069092, "min": -31.999601677060127, "max": 132.91879758238792, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024342171410157615, "min": 0.02337623843198721, "max": 7.05536123858217, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9230315414024517, "min": 1.9168515514229512, "max": 119.94114105589688, "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": "1695025218", "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 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695027481" }, "total": 2263.285930822, "count": 1, "self": 0.933109236999826, "children": { "run_training.setup": { "total": 0.06547624299992094, "count": 1, "self": 0.06547624299992094 }, "TrainerController.start_learning": { "total": 2262.287345342, "count": 1, "self": 1.4751812599838559, "children": { "TrainerController._reset_env": { "total": 4.415550337000013, "count": 1, "self": 4.415550337000013 }, "TrainerController.advance": { "total": 2256.2436118720166, "count": 63845, "self": 1.5853010180044294, "children": { "env_step": { "total": 1585.5851305680912, "count": 63845, "self": 1471.8262028110714, "children": { "SubprocessEnvManager._take_step": { "total": 112.86362152596791, "count": 63845, "self": 4.909817145957618, "children": { "TorchPolicy.evaluate": { "total": 107.9538043800103, "count": 62559, "self": 107.9538043800103 } } }, "workers": { "total": 0.8953062310519044, "count": 63845, "self": 0.0, "children": { "worker_root": { "total": 2256.564804675958, "count": 63845, "is_parallel": true, "self": 903.7736593989355, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005831265999972857, "count": 1, "is_parallel": true, "self": 0.0044828950000237455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013483709999491111, "count": 8, "is_parallel": true, "self": 0.0013483709999491111 } } }, "UnityEnvironment.step": { "total": 0.0478181380000251, "count": 1, "is_parallel": true, "self": 0.0005925349998960883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004960820000405874, "count": 1, "is_parallel": true, "self": 0.0004960820000405874 }, "communicator.exchange": { "total": 0.044123997000042436, "count": 1, "is_parallel": true, "self": 0.044123997000042436 }, "steps_from_proto": { "total": 0.002605524000045989, "count": 1, "is_parallel": true, "self": 0.00034878899987234036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022567350001736486, "count": 8, "is_parallel": true, "self": 0.0022567350001736486 } } } } } } }, "UnityEnvironment.step": { "total": 1352.7911452770225, "count": 63844, "is_parallel": true, "self": 35.16765595914808, "children": { "UnityEnvironment._generate_step_input": { "total": 23.340961099924925, "count": 63844, "is_parallel": true, "self": 23.340961099924925 }, "communicator.exchange": { "total": 1185.3573915550162, "count": 63844, "is_parallel": true, "self": 1185.3573915550162 }, "steps_from_proto": { "total": 108.92513666293326, "count": 63844, "is_parallel": true, "self": 21.468752651960244, "children": { "_process_rank_one_or_two_observation": { "total": 87.45638401097301, "count": 510752, "is_parallel": true, "self": 87.45638401097301 } } } } } } } } } } }, "trainer_advance": { "total": 669.073180285921, "count": 63845, "self": 2.776873529909153, "children": { "process_trajectory": { "total": 114.42531262701334, "count": 63845, "self": 114.1460255510134, "children": { "RLTrainer._checkpoint": { "total": 0.27928707599994596, "count": 2, "self": 0.27928707599994596 } } }, "_update_policy": { "total": 551.8709941289985, "count": 451, "self": 359.0061814290377, "children": { "TorchPPOOptimizer.update": { "total": 192.8648126999608, "count": 22812, "self": 192.8648126999608 } } } } } } }, "trainer_threads": { "total": 1.3359999684325885e-06, "count": 1, "self": 1.3359999684325885e-06 }, "TrainerController._save_models": { "total": 0.15300053700002536, "count": 1, "self": 0.001984392999929696, "children": { "RLTrainer._checkpoint": { "total": 0.15101614400009566, "count": 1, "self": 0.15101614400009566 } } } } } } }