{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.09415225684642792, "min": 0.08482716977596283, "max": 1.465404987335205, "count": 333 }, "Pyramids.Policy.Entropy.sum": { "value": 2821.554931640625, "min": 2541.09326171875, "max": 44454.52734375, "count": 333 }, "Pyramids.Step.mean": { "value": 9989960.0, "min": 29952.0, "max": 9989960.0, "count": 333 }, "Pyramids.Step.sum": { "value": 9989960.0, "min": 29952.0, "max": 9989960.0, "count": 333 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.879218578338623, "min": -0.11492117494344711, "max": 0.9758012890815735, "count": 333 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 276.953857421875, "min": -27.696002960205078, "max": 308.35321044921875, "count": 333 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00444168783724308, "min": -0.0692683681845665, "max": 0.12789200246334076, "count": 333 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3991316556930542, "min": -16.416603088378906, "max": 30.821971893310547, "count": 333 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06583894160964217, "min": 0.06367550048370114, "max": 0.07455933317394518, "count": 333 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9875841241446325, "min": 0.5129392023819522, "max": 1.0788552170561163, "count": 333 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015830561106041488, "min": 0.0003024387323516903, "max": 0.016621780484311184, "count": 333 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23745841659062233, "min": 0.003326826055868593, "max": 0.23745841659062233, "count": 333 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.467397511200008e-07, "min": 7.467397511200008e-07, "max": 0.0002995150630187886, "count": 333 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.1201096266800012e-05, "min": 1.1201096266800012e-05, "max": 0.00426380608873133, "count": 333 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10024888000000003, "min": 0.10024888000000003, "max": 0.1998383542857143, "count": 333 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5037332000000003, "min": 1.3988684800000002, "max": 2.9212686699999995, "count": 333 }, "Pyramids.Policy.Beta.mean": { "value": 3.486311200000002e-05, "min": 3.486311200000002e-05, "max": 0.009983851593142858, "count": 333 }, "Pyramids.Policy.Beta.sum": { "value": 0.0005229466800000004, "min": 0.0005229466800000004, "max": 0.14213474013299998, "count": 333 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0034056615550071, "min": 0.0030794397462159395, "max": 0.2618658244609833, "count": 333 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05108492448925972, "min": 0.04311215505003929, "max": 1.8330607414245605, "count": 333 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 180.64596273291926, "min": 175.30722891566265, "max": 999.0, "count": 333 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29084.0, "min": 15984.0, "max": 32394.0, "count": 333 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8065062367822975, "min": -1.0000000521540642, "max": 1.8215253016428103, "count": 333 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 289.0409978851676, "min": -32.000001668930054, "max": 301.6849984675646, "count": 333 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8065062367822975, "min": -1.0000000521540642, "max": 1.8215253016428103, "count": 333 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 289.0409978851676, "min": -32.000001668930054, "max": 301.6849984675646, "count": 333 }, "Pyramids.Policy.RndReward.mean": { "value": 0.006481339377842232, "min": 0.006260479420072884, "max": 5.24297820776701, "count": 333 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0370143004547572, "min": 0.9679832722467836, "max": 83.88765132427216, "count": 333 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722512291", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722538952" }, "total": 26661.111411746002, "count": 1, "self": 0.8567181170037657, "children": { "run_training.setup": { "total": 0.051401359000010416, "count": 1, "self": 0.051401359000010416 }, "TrainerController.start_learning": { "total": 26660.20329227, "count": 1, "self": 16.17756000224108, "children": { "TrainerController._reset_env": { "total": 2.196116080000138, "count": 1, "self": 2.196116080000138 }, "TrainerController.advance": { "total": 26641.70524422375, "count": 658599, "self": 16.511086704711488, "children": { "env_step": { "total": 20138.63132490517, "count": 658599, "self": 18730.10765029726, "children": { "SubprocessEnvManager._take_step": { "total": 1398.6677477886096, "count": 658599, "self": 49.80586683997717, "children": { "TorchPolicy.evaluate": { "total": 1348.8618809486325, "count": 625054, "self": 1348.8618809486325 } } }, "workers": { "total": 9.855926819301203, "count": 658599, "self": 0.0, "children": { "worker_root": { "total": 26603.930708734515, "count": 658599, "is_parallel": true, "self": 9201.896007512616, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002112764000230527, "count": 1, "is_parallel": true, "self": 0.000688891999743646, "children": { "_process_rank_one_or_two_observation": { "total": 0.001423872000486881, "count": 8, "is_parallel": true, "self": 0.001423872000486881 } } }, "UnityEnvironment.step": { "total": 0.07686732899946946, "count": 1, "is_parallel": true, "self": 0.000653623999824049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004800950000571902, "count": 1, "is_parallel": true, "self": 0.0004800950000571902 }, "communicator.exchange": { "total": 0.07393859599960706, "count": 1, "is_parallel": true, "self": 0.07393859599960706 }, "steps_from_proto": { "total": 0.0017950139999811654, "count": 1, "is_parallel": true, "self": 0.00037360500027716625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014214089997039991, "count": 8, "is_parallel": true, "self": 0.0014214089997039991 } } } } } } }, "UnityEnvironment.step": { "total": 17402.0347012219, "count": 658598, "is_parallel": true, "self": 354.394534758394, "children": { "UnityEnvironment._generate_step_input": { "total": 244.4574031311331, "count": 658598, "is_parallel": true, "self": 244.4574031311331 }, "communicator.exchange": { "total": 15757.162520155973, "count": 658598, "is_parallel": true, "self": 15757.162520155973 }, "steps_from_proto": { "total": 1046.0202431763983, "count": 658598, "is_parallel": true, "self": 222.55408887480553, "children": { "_process_rank_one_or_two_observation": { "total": 823.4661543015927, "count": 5268784, "is_parallel": true, "self": 823.4661543015927 } } } } } } } } } } }, "trainer_advance": { "total": 6486.5628326138685, "count": 658599, "self": 31.80964322697855, "children": { "process_trajectory": { "total": 1390.7876757999993, "count": 658599, "self": 1388.785776337002, "children": { "RLTrainer._checkpoint": { "total": 2.001899462997244, "count": 20, "self": 2.001899462997244 } } }, "_update_policy": { "total": 5063.965513586891, "count": 4704, "self": 3011.5382004525327, "children": { "TorchPPOOptimizer.update": { "total": 2052.427313134358, "count": 227961, "self": 2052.427313134358 } } } } } } }, "trainer_threads": { "total": 1.4220058801583946e-06, "count": 1, "self": 1.4220058801583946e-06 }, "TrainerController._save_models": { "total": 0.12437054199835984, "count": 1, "self": 0.002335873999982141, "children": { "RLTrainer._checkpoint": { "total": 0.1220346679983777, "count": 1, "self": 0.1220346679983777 } } } } } } }