{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38188955187797546, "min": 0.38188955187797546, "max": 1.501266598701477, "count": 38 }, "Pyramids.Policy.Entropy.sum": { "value": 11572.78125, "min": 11572.78125, "max": 45542.421875, "count": 38 }, "Pyramids.Step.mean": { "value": 1139999.0, "min": 29950.0, "max": 1139999.0, "count": 38 }, "Pyramids.Step.sum": { "value": 1139999.0, "min": 29950.0, "max": 1139999.0, "count": 38 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6691520810127258, "min": -0.11134287714958191, "max": 0.755984902381897, "count": 38 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 198.73817443847656, "min": -26.833633422851562, "max": 218.47962951660156, "count": 38 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002073489362373948, "min": -0.04220078885555267, "max": 0.3586871325969696, "count": 38 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6158263683319092, "min": -11.014406204223633, "max": 85.00885009765625, "count": 38 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07053040664398316, "min": 0.0661051647970453, "max": 0.07343601807104085, "count": 38 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9874256930157643, "min": 0.506370608525079, "max": 1.0320668164931703, "count": 38 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01595725925396006, "min": 0.0006119679733746128, "max": 0.01595725925396006, "count": 38 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22340162955544082, "min": 0.007955583653869967, "max": 0.22474448316315115, "count": 38 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001874605732274405, "min": 0.0001874605732274405, "max": 0.0002984110005296667, "count": 38 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002624448025184167, "min": 0.002088877003707667, "max": 0.0038007931330689996, "count": 38 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16248684523809526, "min": 0.16248684523809526, "max": 0.19947033333333336, "count": 38 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2748158333333337, "min": 1.3962923333333335, "max": 2.692464433333333, "count": 38 }, "Pyramids.Policy.Beta.mean": { "value": 0.006252435839285714, "min": 0.006252435839285714, "max": 0.0099470863, "count": 38 }, "Pyramids.Policy.Beta.sum": { "value": 0.08753410175, "min": 0.06962960409999999, "max": 0.12670640689999998, "count": 38 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008175112307071686, "min": 0.007788532413542271, "max": 0.35342660546302795, "count": 38 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1144515722990036, "min": 0.1095438003540039, "max": 2.4739861488342285, "count": 38 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.67289719626166, "min": 264.08035714285717, "max": 999.0, "count": 38 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30888.0, "min": 16621.0, "max": 34094.0, "count": 38 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6739345651085131, "min": -1.0000000521540642, "max": 1.7180606918409467, "count": 38 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 179.1109984666109, "min": -32.000001668930054, "max": 192.42279748618603, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6739345651085131, "min": -1.0000000521540642, "max": 1.7180606918409467, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 179.1109984666109, "min": -32.000001668930054, "max": 192.42279748618603, "count": 38 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02430717246081989, "min": 0.02430717246081989, "max": 6.620569071348975, "count": 38 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6008674533077283, "min": 2.2279771442554193, "max": 112.54967421293259, "count": 38 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 38 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 38 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1768338498", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1768341010" }, "total": 2512.588613391, "count": 1, "self": 0.5052783890000683, "children": { "run_training.setup": { "total": 0.022476386000107595, "count": 1, "self": 0.022476386000107595 }, "TrainerController.start_learning": { "total": 2512.0608586159997, "count": 1, "self": 1.618787881015578, "children": { "TrainerController._reset_env": { "total": 2.000398597000185, "count": 1, "self": 2.000398597000185 }, "TrainerController.advance": { "total": 2508.263030581984, "count": 73243, "self": 1.6506406379749023, "children": { "env_step": { "total": 1768.7173214021482, "count": 73243, "self": 1594.5715477281192, "children": { "SubprocessEnvManager._take_step": { "total": 173.14291946004641, "count": 73243, "self": 5.264045809934942, "children": { "TorchPolicy.evaluate": { "total": 167.87887365011147, "count": 71641, "self": 167.87887365011147 } } }, "workers": { "total": 1.0028542139825731, "count": 73242, "self": 0.0, "children": { "worker_root": { "total": 2504.750773728044, "count": 73242, "is_parallel": true, "self": 1045.0704402040892, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016284260000247741, "count": 1, "is_parallel": true, "self": 0.0004998580002393282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011285679997854459, "count": 8, "is_parallel": true, "self": 0.0011285679997854459 } } }, "UnityEnvironment.step": { "total": 0.04967214399994191, "count": 1, "is_parallel": true, "self": 0.0005460500001390756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000509201000113535, "count": 1, "is_parallel": true, "self": 0.000509201000113535 }, "communicator.exchange": { "total": 0.04691357099954985, "count": 1, "is_parallel": true, "self": 0.04691357099954985 }, "steps_from_proto": { "total": 0.0017033220001394511, "count": 1, "is_parallel": true, "self": 0.00034726899957604473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013560530005634064, "count": 8, "is_parallel": true, "self": 0.0013560530005634064 } } } } } } }, "UnityEnvironment.step": { "total": 1459.6803335239547, "count": 73241, "is_parallel": true, "self": 38.03736068719172, "children": { "UnityEnvironment._generate_step_input": { "total": 26.45456565491577, "count": 73241, "is_parallel": true, "self": 26.45456565491577 }, "communicator.exchange": { "total": 1274.436042397895, "count": 73241, "is_parallel": true, "self": 1274.436042397895 }, "steps_from_proto": { "total": 120.75236478395209, "count": 73241, "is_parallel": true, "self": 25.485454056859453, "children": { "_process_rank_one_or_two_observation": { "total": 95.26691072709264, "count": 585928, "is_parallel": true, "self": 95.26691072709264 } } } } } } } } } } }, "trainer_advance": { "total": 737.8950685418608, "count": 73242, "self": 3.0947183007647254, "children": { "process_trajectory": { "total": 139.074340333098, "count": 73242, "self": 138.8962951410981, "children": { "RLTrainer._checkpoint": { "total": 0.17804519199989954, "count": 2, "self": 0.17804519199989954 } } }, "_update_policy": { "total": 595.7260099079981, "count": 514, "self": 332.53715679293373, "children": { "TorchPPOOptimizer.update": { "total": 263.1888531150644, "count": 26127, "self": 263.1888531150644 } } } } } } }, "trainer_threads": { "total": 1.6100002540042624e-06, "count": 1, "self": 1.6100002540042624e-06 }, "TrainerController._save_models": { "total": 0.1786399459997483, "count": 1, "self": 0.005350548999558669, "children": { "RLTrainer._checkpoint": { "total": 0.17328939700018964, "count": 1, "self": 0.17328939700018964 } } } } } } }