{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6612257361412048, "min": 0.6612257361412048, "max": 1.3829609155654907, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19678.078125, "min": 19678.078125, "max": 41953.50390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0627322718501091, "min": -0.11199305951595306, "max": 0.09172578901052475, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 15.432138442993164, "min": -27.102319717407227, "max": 22.656269073486328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02176976017653942, "min": 0.007074796594679356, "max": 0.35083121061325073, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.355360984802246, "min": 1.7474747896194458, "max": 84.19949340820312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850646806835832, "min": 0.06398289415049703, "max": 0.07310759250863705, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9590905529570164, "min": 0.4798651467052846, "max": 1.0437771753045928, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005933725971596435, "min": 0.0002992366546125215, "max": 0.005982384877318827, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08307216360235009, "min": 0.002992366546125215, "max": 0.08307216360235009, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.464118940564287e-06, "min": 7.464118940564287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010449766516790002, "min": 0.00010449766516790002, "max": 0.0030207608930798, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248800714285713, "min": 0.10248800714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348321, "min": 1.3691136000000002, "max": 2.359057, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585519135714287, "min": 0.0002585519135714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003619726790000002, "min": 0.003619726790000002, "max": 0.10072132798, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014452091418206692, "min": 0.014279200695455074, "max": 0.42627301812171936, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20232927799224854, "min": 0.20070239901542664, "max": 2.9839110374450684, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 805.4, "min": 795.5263157894736, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28189.0, "min": 15984.0, "max": 32406.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.28002281444413324, "min": -1.0000000521540642, "max": 0.28002281444413324, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 9.800798505544662, "min": -32.000001668930054, "max": 9.800798505544662, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.28002281444413324, "min": -1.0000000521540642, "max": 0.28002281444413324, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 9.800798505544662, "min": -32.000001668930054, "max": 9.800798505544662, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12133785032866788, "min": 0.11832984130925094, "max": 8.416626082733274, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.246824761503376, "min": 4.213088566903025, "max": 134.66601732373238, "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": "1742555351", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742557830" }, "total": 2479.1611598629997, "count": 1, "self": 0.5758834610001031, "children": { "run_training.setup": { "total": 0.034341406999828905, "count": 1, "self": 0.034341406999828905 }, "TrainerController.start_learning": { "total": 2478.550934995, "count": 1, "self": 2.433458263002649, "children": { "TrainerController._reset_env": { "total": 2.978400418000092, "count": 1, "self": 2.978400418000092 }, "TrainerController.advance": { "total": 2473.0697424669975, "count": 63162, "self": 2.4555728870204803, "children": { "env_step": { "total": 1645.1093814070057, "count": 63162, "self": 1487.5745012469147, "children": { "SubprocessEnvManager._take_step": { "total": 156.12895080501517, "count": 63162, "self": 6.11167329604973, "children": { "TorchPolicy.evaluate": { "total": 150.01727750896544, "count": 62546, "self": 150.01727750896544 } } }, "workers": { "total": 1.4059293550758412, "count": 63162, "self": 0.0, "children": { "worker_root": { "total": 2471.5795739230416, "count": 63162, "is_parallel": true, "self": 1141.1593669769836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004115429999956177, "count": 1, "is_parallel": true, "self": 0.0016213500002777437, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024940799996784335, "count": 8, "is_parallel": true, "self": 0.0024940799996784335 } } }, "UnityEnvironment.step": { "total": 0.07220375299993975, "count": 1, "is_parallel": true, "self": 0.0005890499996894505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000539300000127696, "count": 1, "is_parallel": true, "self": 0.000539300000127696 }, "communicator.exchange": { "total": 0.06930812300015532, "count": 1, "is_parallel": true, "self": 0.06930812300015532 }, "steps_from_proto": { "total": 0.0017672799999672861, "count": 1, "is_parallel": true, "self": 0.0003825600001619023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013847199998053838, "count": 8, "is_parallel": true, "self": 0.0013847199998053838 } } } } } } }, "UnityEnvironment.step": { "total": 1330.420206946058, "count": 63161, "is_parallel": true, "self": 38.685660551049295, "children": { "UnityEnvironment._generate_step_input": { "total": 27.595473760981577, "count": 63161, "is_parallel": true, "self": 27.595473760981577 }, "communicator.exchange": { "total": 1162.6839711710654, "count": 63161, "is_parallel": true, "self": 1162.6839711710654 }, "steps_from_proto": { "total": 101.4551014629617, "count": 63161, "is_parallel": true, "self": 23.00321879287071, "children": { "_process_rank_one_or_two_observation": { "total": 78.45188267009098, "count": 505288, "is_parallel": true, "self": 78.45188267009098 } } } } } } } } } } }, "trainer_advance": { "total": 825.5047881729715, "count": 63162, "self": 4.589303499991047, "children": { "process_trajectory": { "total": 138.26821690098018, "count": 63162, "self": 137.73092742998028, "children": { "RLTrainer._checkpoint": { "total": 0.5372894709998945, "count": 2, "self": 0.5372894709998945 } } }, "_update_policy": { "total": 682.6472677720003, "count": 433, "self": 264.3730516609744, "children": { "TorchPPOOptimizer.update": { "total": 418.2742161110259, "count": 22863, "self": 418.2742161110259 } } } } } } }, "trainer_threads": { "total": 1.4299998838396277e-06, "count": 1, "self": 1.4299998838396277e-06 }, "TrainerController._save_models": { "total": 0.06933241699971404, "count": 1, "self": 0.0014144899996608729, "children": { "RLTrainer._checkpoint": { "total": 0.06791792700005317, "count": 1, "self": 0.06791792700005317 } } } } } } }