{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5524945855140686, "min": 0.5524945855140686, "max": 1.4562660455703735, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16663.236328125, "min": 16663.236328125, "max": 44177.28515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4408276081085205, "min": -0.10384897142648697, "max": 0.5109353065490723, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.70097351074219, "min": -25.02760124206543, "max": 138.97439575195312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.042670246213674545, "min": -0.005379129201173782, "max": 0.5939338803291321, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.392955780029297, "min": -1.4254692792892456, "max": 140.7623291015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0698959530577884, "min": 0.06578722529645477, "max": 0.07416518300150735, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9785433428090375, "min": 0.5191562810105514, "max": 1.0627877745913186, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012656766772124683, "min": 0.0004185371908981604, "max": 0.01604220723404033, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17719473480974557, "min": 0.005440983481676085, "max": 0.22459090127656464, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.400261818992853e-06, "min": 7.400261818992853e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010360366546589995, "min": 0.00010360366546589995, "max": 0.0036323854892049, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246672142857145, "min": 0.10246672142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345341000000003, "min": 1.3886848, "max": 2.6107951000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002564254707142856, "min": 0.0002564254707142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003589956589999998, "min": 0.003589956589999998, "max": 0.12109843049, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012180747464299202, "min": 0.012180747464299202, "max": 0.6504069566726685, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17053046822547913, "min": 0.17053046822547913, "max": 4.552848815917969, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.02666666666664, "min": 376.8987341772152, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28652.0, "min": 15984.0, "max": 33319.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4011891681600261, "min": -1.0000000521540642, "max": 1.5559522127037617, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.68799844384193, "min": -29.893401622772217, "max": 124.35419829189777, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4011891681600261, "min": -1.0000000521540642, "max": 1.5559522127037617, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.68799844384193, "min": -29.893401622772217, "max": 124.35419829189777, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0484403507828058, "min": 0.0484403507828058, "max": 14.18575663678348, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5845859579276294, "min": 3.5845859579276294, "max": 226.9721061885357, "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": "1709610956", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709613248" }, "total": 2291.192968002, "count": 1, "self": 0.49064843599990127, "children": { "run_training.setup": { "total": 0.05303181900001164, "count": 1, "self": 0.05303181900001164 }, "TrainerController.start_learning": { "total": 2290.649287747, "count": 1, "self": 1.7218490310283414, "children": { "TrainerController._reset_env": { "total": 2.6054252709999446, "count": 1, "self": 2.6054252709999446 }, "TrainerController.advance": { "total": 2286.231694432972, "count": 63587, "self": 1.779844503014374, "children": { "env_step": { "total": 1622.171432412999, "count": 63587, "self": 1473.8819828590542, "children": { "SubprocessEnvManager._take_step": { "total": 147.25086026796487, "count": 63587, "self": 5.2908563059164635, "children": { "TorchPolicy.evaluate": { "total": 141.9600039620484, "count": 62554, "self": 141.9600039620484 } } }, "workers": { "total": 1.0385892859798105, "count": 63587, "self": 0.0, "children": { "worker_root": { "total": 2284.7332684400358, "count": 63587, "is_parallel": true, "self": 942.5275370170257, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022107470000491958, "count": 1, "is_parallel": true, "self": 0.0006720220001170674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015387249999321284, "count": 8, "is_parallel": true, "self": 0.0015387249999321284 } } }, "UnityEnvironment.step": { "total": 0.051455013000008876, "count": 1, "is_parallel": true, "self": 0.0005860870001015428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005075699999679273, "count": 1, "is_parallel": true, "self": 0.0005075699999679273 }, "communicator.exchange": { "total": 0.04873682400000234, "count": 1, "is_parallel": true, "self": 0.04873682400000234 }, "steps_from_proto": { "total": 0.0016245319999370622, "count": 1, "is_parallel": true, "self": 0.00036237999995591963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012621519999811426, "count": 8, "is_parallel": true, "self": 0.0012621519999811426 } } } } } } }, "UnityEnvironment.step": { "total": 1342.20573142301, "count": 63586, "is_parallel": true, "self": 38.298545964004006, "children": { "UnityEnvironment._generate_step_input": { "total": 25.708128131006333, "count": 63586, "is_parallel": true, "self": 25.708128131006333 }, "communicator.exchange": { "total": 1171.176087752975, "count": 63586, "is_parallel": true, "self": 1171.176087752975 }, "steps_from_proto": { "total": 107.0229695750246, "count": 63586, "is_parallel": true, "self": 22.34017217711778, "children": { "_process_rank_one_or_two_observation": { "total": 84.68279739790682, "count": 508688, "is_parallel": true, "self": 84.68279739790682 } } } } } } } } } } }, "trainer_advance": { "total": 662.2804175169583, "count": 63587, "self": 3.234152949935151, "children": { "process_trajectory": { "total": 130.72451477002983, "count": 63587, "self": 130.51146724402975, "children": { "RLTrainer._checkpoint": { "total": 0.21304752600008214, "count": 2, "self": 0.21304752600008214 } } }, "_update_policy": { "total": 528.3217497969933, "count": 455, "self": 310.0499867899704, "children": { "TorchPPOOptimizer.update": { "total": 218.27176300702297, "count": 22797, "self": 218.27176300702297 } } } } } } }, "trainer_threads": { "total": 9.099999260797631e-07, "count": 1, "self": 9.099999260797631e-07 }, "TrainerController._save_models": { "total": 0.09031810199985557, "count": 1, "self": 0.0013789129998258431, "children": { "RLTrainer._checkpoint": { "total": 0.08893918900002973, "count": 1, "self": 0.08893918900002973 } } } } } } }