{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5923354625701904, "min": 0.5923354625701904, "max": 1.453642725944519, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17770.064453125, "min": 17759.767578125, "max": 44097.70703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29965.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29965.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3344428837299347, "min": -0.0984574481844902, "max": 0.34629690647125244, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 88.62736511230469, "min": -23.72824478149414, "max": 90.38349151611328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05180658772587776, "min": -0.28089454770088196, "max": 0.35120537877082825, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.728745460510254, "min": -69.66184997558594, "max": 90.25978088378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06997550553448188, "min": 0.06425170784352797, "max": 0.07310933458437593, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9796570774827463, "min": 0.582261218396315, "max": 1.041276920989142, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012712154459829133, "min": 0.0008688371122270388, "max": 0.02862670648358312, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17797016243760785, "min": 0.010426045346724465, "max": 0.4007738907701637, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4385546633714305e-06, "min": 7.4385546633714305e-06, "max": 0.0002948529392156875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010413976528720003, "min": 0.00010413976528720003, "max": 0.0035072252309249997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247948571428574, "min": 0.10247948571428574, "max": 0.1982843125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347128000000002, "min": 1.4347128000000002, "max": 2.5690749999999993, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025770062285714295, "min": 0.00025770062285714295, "max": 0.00982860281875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036078087200000016, "min": 0.0036078087200000016, "max": 0.11693059250000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010181399993598461, "min": 0.010181399993598461, "max": 0.3752458989620209, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1425396054983139, "min": 0.1425396054983139, "max": 3.001967191696167, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 484.36507936507934, "min": 484.36507936507934, "max": 995.125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30515.0, "min": 16380.0, "max": 32314.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2616031470279845, "min": -0.9335688014980406, "max": 1.2966101457506924, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 79.48099826276302, "min": -30.3302016928792, "max": 79.48099826276302, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2616031470279845, "min": -0.9335688014980406, "max": 1.2966101457506924, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 79.48099826276302, "min": -30.3302016928792, "max": 79.48099826276302, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05217204827400449, "min": 0.05217204827400449, "max": 7.4629862904548645, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.286839041262283, "min": 3.1645436639664695, "max": 126.8707669377327, "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": "1693278128", "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", "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": "1693280301" }, "total": 2172.348605834, "count": 1, "self": 0.9464471530000083, "children": { "run_training.setup": { "total": 0.03929160200004844, "count": 1, "self": 0.03929160200004844 }, "TrainerController.start_learning": { "total": 2171.362867079, "count": 1, "self": 1.3687063490865512, "children": { "TrainerController._reset_env": { "total": 4.165315903000192, "count": 1, "self": 4.165315903000192 }, "TrainerController.advance": { "total": 2165.675295324913, "count": 63476, "self": 1.465319106950119, "children": { "env_step": { "total": 1491.1658271249685, "count": 63476, "self": 1380.6189804020503, "children": { "SubprocessEnvManager._take_step": { "total": 109.6901809039673, "count": 63476, "self": 4.712852147020385, "children": { "TorchPolicy.evaluate": { "total": 104.97732875694692, "count": 62563, "self": 104.97732875694692 } } }, "workers": { "total": 0.8566658189508871, "count": 63476, "self": 0.0, "children": { "worker_root": { "total": 2166.253374350974, "count": 63476, "is_parallel": true, "self": 899.4275699979933, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018353539999225177, "count": 1, "is_parallel": true, "self": 0.00057408999987274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012612640000497777, "count": 8, "is_parallel": true, "self": 0.0012612640000497777 } } }, "UnityEnvironment.step": { "total": 0.04719254699989506, "count": 1, "is_parallel": true, "self": 0.0005619129999558936, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044521199993141636, "count": 1, "is_parallel": true, "self": 0.00044521199993141636 }, "communicator.exchange": { "total": 0.04432291600005556, "count": 1, "is_parallel": true, "self": 0.04432291600005556 }, "steps_from_proto": { "total": 0.001862505999952191, "count": 1, "is_parallel": true, "self": 0.00036607999936677516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014964260005854157, "count": 8, "is_parallel": true, "self": 0.0014964260005854157 } } } } } } }, "UnityEnvironment.step": { "total": 1266.8258043529806, "count": 63475, "is_parallel": true, "self": 33.885897840031475, "children": { "UnityEnvironment._generate_step_input": { "total": 22.451233962985725, "count": 63475, "is_parallel": true, "self": 22.451233962985725 }, "communicator.exchange": { "total": 1105.4327092980307, "count": 63475, "is_parallel": true, "self": 1105.4327092980307 }, "steps_from_proto": { "total": 105.05596325193278, "count": 63475, "is_parallel": true, "self": 20.5368303991188, "children": { "_process_rank_one_or_two_observation": { "total": 84.51913285281398, "count": 507800, "is_parallel": true, "self": 84.51913285281398 } } } } } } } } } } }, "trainer_advance": { "total": 673.0441490929943, "count": 63476, "self": 2.6526126299525004, "children": { "process_trajectory": { "total": 111.22933297604277, "count": 63476, "self": 110.97428075304333, "children": { "RLTrainer._checkpoint": { "total": 0.2550522229994385, "count": 2, "self": 0.2550522229994385 } } }, "_update_policy": { "total": 559.162203486999, "count": 453, "self": 364.15018279099013, "children": { "TorchPPOOptimizer.update": { "total": 195.0120206960089, "count": 22779, "self": 195.0120206960089 } } } } } } }, "trainer_threads": { "total": 1.4360002751345746e-06, "count": 1, "self": 1.4360002751345746e-06 }, "TrainerController._save_models": { "total": 0.15354806599998483, "count": 1, "self": 0.001977783999791427, "children": { "RLTrainer._checkpoint": { "total": 0.1515702820001934, "count": 1, "self": 0.1515702820001934 } } } } } } }