{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48494869470596313, "min": 0.4458564817905426, "max": 1.4305806159973145, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14494.146484375, "min": 13582.572265625, "max": 43398.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4544605016708374, "min": -0.09257080405950546, "max": 0.4753778874874115, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.2498779296875, "min": -22.21699333190918, "max": 127.40127563476562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01365196518599987, "min": -0.05046461150050163, "max": 0.5272053480148315, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6723785400390625, "min": -12.666617393493652, "max": 124.94766998291016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06907490241267596, "min": 0.06545852637549142, "max": 0.07361949516972796, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9670486337774633, "min": 0.5005067759424303, "max": 1.0682951432293823, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015097734185632063, "min": 0.0003599718032271872, "max": 0.01654348267904771, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21136827859884888, "min": 0.0025198026225903103, "max": 0.2316087575066679, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.622990316178575e-06, "min": 7.622990316178575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010672186442650005, "min": 0.00010672186442650005, "max": 0.0029091435302856005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254096428571428, "min": 0.10254096428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355735, "min": 1.327104, "max": 2.3597314000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026384233214285724, "min": 0.00026384233214285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036937926500000017, "min": 0.0036937926500000017, "max": 0.09700446856, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011389526538550854, "min": 0.011389526538550854, "max": 0.48789069056510925, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1594533771276474, "min": 0.1594533771276474, "max": 3.4152348041534424, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.8550724637681, "min": 397.6764705882353, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31040.0, "min": 15984.0, "max": 32843.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4921622930661491, "min": -1.0000000521540642, "max": 1.5434852777158512, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 102.9591982215643, "min": -32.000001668930054, "max": 112.33799807727337, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4921622930661491, "min": -1.0000000521540642, "max": 1.5434852777158512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 102.9591982215643, "min": -32.000001668930054, "max": 112.33799807727337, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052687975265882044, "min": 0.04797114216746516, "max": 10.168355417437851, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.635470293345861, "min": 3.262037667387631, "max": 162.69368667900562, "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": "1727817054", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727820396" }, "total": 3342.0822148019997, "count": 1, "self": 0.6559751639997558, "children": { "run_training.setup": { "total": 0.08156471999996029, "count": 1, "self": 0.08156471999996029 }, "TrainerController.start_learning": { "total": 3341.3446749180002, "count": 1, "self": 2.3904796399083352, "children": { "TrainerController._reset_env": { "total": 3.720933862000038, "count": 1, "self": 3.720933862000038 }, "TrainerController.advance": { "total": 3335.1375806090923, "count": 63529, "self": 2.5486039721531597, "children": { "env_step": { "total": 2185.466810155028, "count": 63529, "self": 2013.308944794122, "children": { "SubprocessEnvManager._take_step": { "total": 170.6680165910018, "count": 63529, "self": 7.257320027049673, "children": { "TorchPolicy.evaluate": { "total": 163.41069656395211, "count": 62570, "self": 163.41069656395211 } } }, "workers": { "total": 1.4898487699040288, "count": 63529, "self": 0.0, "children": { "worker_root": { "total": 3333.8334394340523, "count": 63529, "is_parallel": true, "self": 1510.5286797009514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006073121000099491, "count": 1, "is_parallel": true, "self": 0.0018826979996902082, "children": { "_process_rank_one_or_two_observation": { "total": 0.004190423000409282, "count": 8, "is_parallel": true, "self": 0.004190423000409282 } } }, "UnityEnvironment.step": { "total": 0.2105785559999731, "count": 1, "is_parallel": true, "self": 0.0008339419998719677, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005338329999631242, "count": 1, "is_parallel": true, "self": 0.0005338329999631242 }, "communicator.exchange": { "total": 0.2012841020000451, "count": 1, "is_parallel": true, "self": 0.2012841020000451 }, "steps_from_proto": { "total": 0.007926679000092918, "count": 1, "is_parallel": true, "self": 0.001978233999807344, "children": { "_process_rank_one_or_two_observation": { "total": 0.005948445000285574, "count": 8, "is_parallel": true, "self": 0.005948445000285574 } } } } } } }, "UnityEnvironment.step": { "total": 1823.3047597331008, "count": 63528, "is_parallel": true, "self": 50.064376761043604, "children": { "UnityEnvironment._generate_step_input": { "total": 30.727613304077977, "count": 63528, "is_parallel": true, "self": 30.727613304077977 }, "communicator.exchange": { "total": 1612.4939331609442, "count": 63528, "is_parallel": true, "self": 1612.4939331609442 }, "steps_from_proto": { "total": 130.01883650703508, "count": 63528, "is_parallel": true, "self": 28.396681895394295, "children": { "_process_rank_one_or_two_observation": { "total": 101.62215461164078, "count": 508224, "is_parallel": true, "self": 101.62215461164078 } } } } } } } } } } }, "trainer_advance": { "total": 1147.1221664819116, "count": 63529, "self": 4.833881795924071, "children": { "process_trajectory": { "total": 172.4370689779828, "count": 63529, "self": 172.18156362698278, "children": { "RLTrainer._checkpoint": { "total": 0.2555053510000107, "count": 2, "self": 0.2555053510000107 } } }, "_update_policy": { "total": 969.8512157080047, "count": 428, "self": 388.923307605055, "children": { "TorchPPOOptimizer.update": { "total": 580.9279081029497, "count": 22845, "self": 580.9279081029497 } } } } } } }, "trainer_threads": { "total": 1.1579995771171525e-06, "count": 1, "self": 1.1579995771171525e-06 }, "TrainerController._save_models": { "total": 0.09567964899997605, "count": 1, "self": 0.002464440000039758, "children": { "RLTrainer._checkpoint": { "total": 0.0932152089999363, "count": 1, "self": 0.0932152089999363 } } } } } } }