{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1699434220790863, "min": 0.1589108556509018, "max": 1.4355571269989014, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5109.17919921875, "min": 4706.3037109375, "max": 43549.0625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999913.0, "min": 29872.0, "max": 2999913.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999913.0, "min": 29872.0, "max": 2999913.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7211897373199463, "min": -0.12625479698181152, "max": 0.8051129579544067, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.70265197753906, "min": -30.427406311035156, "max": 245.5594482421875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006519346032291651, "min": -0.028734033927321434, "max": 0.5028015971183777, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.877571702003479, "min": -8.217933654785156, "max": 119.16397857666016, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06946581515906013, "min": 0.0642460925461847, "max": 0.07343506729622501, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9725214122268417, "min": 0.5874805383698001, "max": 1.0735731620550402, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01597470379906057, "min": 0.0009759758925796041, "max": 0.01793606247346837, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.223645853186848, "min": 0.00975975892579604, "max": 0.2647530655473626, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5154923520119046e-06, "min": 1.5154923520119046e-06, "max": 0.00029828300057233335, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1216892928166664e-05, "min": 2.1216892928166664e-05, "max": 0.0038431359189547327, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050513095238098, "min": 0.10050513095238098, "max": 0.1994276666666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070718333333336, "min": 1.4070718333333336, "max": 2.7525887666666673, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.046258214285713e-05, "min": 6.046258214285713e-05, "max": 0.0099428239, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008464761499999998, "min": 0.0008464761499999998, "max": 0.12811642214000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006478712894022465, "min": 0.006248242221772671, "max": 0.4561033248901367, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09070198237895966, "min": 0.08747538924217224, "max": 3.6488265991210938, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.60550458715596, "min": 232.89166666666668, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28515.0, "min": 16415.0, "max": 32959.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6839381722564046, "min": -1.0000000521540642, "max": 1.764935984492302, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.23319894820452, "min": -32.000001668930054, "max": 221.2677979543805, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6839381722564046, "min": -1.0000000521540642, "max": 1.764935984492302, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.23319894820452, "min": -32.000001668930054, "max": 221.2677979543805, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01761274554287824, "min": 0.016503263980516426, "max": 9.160996058407951, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9374020097166067, "min": 1.9374020097166067, "max": 155.73693299293518, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707379365", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707386556" }, "total": 7191.2914315689995, "count": 1, "self": 0.7051619189996927, "children": { "run_training.setup": { "total": 0.04907144599997082, "count": 1, "self": 0.04907144599997082 }, "TrainerController.start_learning": { "total": 7190.537198204, "count": 1, "self": 4.257185102771473, "children": { "TrainerController._reset_env": { "total": 3.172968016000027, "count": 1, "self": 3.172968016000027 }, "TrainerController.advance": { "total": 7182.957925646228, "count": 194222, "self": 4.395558660080496, "children": { "env_step": { "total": 5317.192187717959, "count": 194222, "self": 4919.294746591776, "children": { "SubprocessEnvManager._take_step": { "total": 395.2775478979802, "count": 194222, "self": 14.429632229943422, "children": { "TorchPolicy.evaluate": { "total": 380.84791566803676, "count": 187558, "self": 380.84791566803676 } } }, "workers": { "total": 2.6198932282032956, "count": 194222, "self": 0.0, "children": { "worker_root": { "total": 7174.250273560954, "count": 194222, "is_parallel": true, "self": 2621.7648643469292, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004647274000035395, "count": 1, "is_parallel": true, "self": 0.003180552000003445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014667220000319503, "count": 8, "is_parallel": true, "self": 0.0014667220000319503 } } }, "UnityEnvironment.step": { "total": 0.05291616299996349, "count": 1, "is_parallel": true, "self": 0.0006407619999890812, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005493870000918832, "count": 1, "is_parallel": true, "self": 0.0005493870000918832 }, "communicator.exchange": { "total": 0.04989766099993176, "count": 1, "is_parallel": true, "self": 0.04989766099993176 }, "steps_from_proto": { "total": 0.0018283529999507664, "count": 1, "is_parallel": true, "self": 0.000379405999865412, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014489470000853544, "count": 8, "is_parallel": true, "self": 0.0014489470000853544 } } } } } } }, "UnityEnvironment.step": { "total": 4552.485409214025, "count": 194221, "is_parallel": true, "self": 109.09329422802602, "children": { "UnityEnvironment._generate_step_input": { "total": 77.92559509609157, "count": 194221, "is_parallel": true, "self": 77.92559509609157 }, "communicator.exchange": { "total": 4050.5191178960376, "count": 194221, "is_parallel": true, "self": 4050.5191178960376 }, "steps_from_proto": { "total": 314.94740199387, "count": 194221, "is_parallel": true, "self": 64.05865931956112, "children": { "_process_rank_one_or_two_observation": { "total": 250.8887426743089, "count": 1553768, "is_parallel": true, "self": 250.8887426743089 } } } } } } } } } } }, "trainer_advance": { "total": 1861.3701792681888, "count": 194222, "self": 8.543580096301184, "children": { "process_trajectory": { "total": 392.09939813789424, "count": 194222, "self": 391.43804200289287, "children": { "RLTrainer._checkpoint": { "total": 0.6613561350013697, "count": 6, "self": 0.6613561350013697 } } }, "_update_policy": { "total": 1460.7272010339934, "count": 1394, "self": 858.5332457681577, "children": { "TorchPPOOptimizer.update": { "total": 602.1939552658357, "count": 68373, "self": 602.1939552658357 } } } } } } }, "trainer_threads": { "total": 1.3110002328176051e-06, "count": 1, "self": 1.3110002328176051e-06 }, "TrainerController._save_models": { "total": 0.14911812799982727, "count": 1, "self": 0.0022649290003755596, "children": { "RLTrainer._checkpoint": { "total": 0.1468531989994517, "count": 1, "self": 0.1468531989994517 } } } } } } }