{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44157305359840393, "min": 0.43676286935806274, "max": 1.4378165006637573, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13141.2138671875, "min": 13123.8505859375, "max": 43617.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29921.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29921.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4675433337688446, "min": -0.10235287994146347, "max": 0.5306376814842224, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.63932800292969, "min": -24.871749877929688, "max": 145.3947296142578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.061313942074775696, "min": -0.007736389525234699, "max": 0.35186150670051575, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.738706588745117, "min": -2.088825225830078, "max": 83.39117431640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07140147745598195, "min": 0.06625515024300993, "max": 0.07321805168272126, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9996206843837474, "min": 0.5125263617790489, "max": 1.0655628848762717, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01638331957933371, "min": 0.0005011507156734543, "max": 0.016899993951018488, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22936647411067193, "min": 0.005095331658197552, "max": 0.2534999092652773, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.659740303928572e-06, "min": 7.659740303928572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010723636425500001, "min": 0.00010723636425500001, "max": 0.0035085839304720996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255321428571429, "min": 0.10255321428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435745, "min": 1.3886848, "max": 2.5695279000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026506610714285714, "min": 0.00026506610714285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037109255, "min": 0.0037109255, "max": 0.11697583720999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013357214629650116, "min": 0.013357214629650116, "max": 0.528098464012146, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18700100481510162, "min": 0.18700100481510162, "max": 3.6966891288757324, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.5, "min": 372.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29055.0, "min": 16848.0, "max": 33148.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.502891117824784, "min": -0.9999500517733395, "max": 1.5760023581484954, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.72839830815792, "min": -31.998401656746864, "max": 132.3841980844736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.502891117824784, "min": -0.9999500517733395, "max": 1.5760023581484954, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.72839830815792, "min": -31.998401656746864, "max": 132.3841980844736, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05053089526308777, "min": 0.05053089526308777, "max": 10.316037229755345, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.991940725783934, "min": 3.991940725783934, "max": 175.37263290584087, "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": "1739968749", "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=Pyramids1 --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": "1739971199" }, "total": 2449.8467404450003, "count": 1, "self": 0.8238253650001752, "children": { "run_training.setup": { "total": 0.026107305999971686, "count": 1, "self": 0.026107305999971686 }, "TrainerController.start_learning": { "total": 2448.996807774, "count": 1, "self": 1.6614750589847063, "children": { "TrainerController._reset_env": { "total": 3.244699923999974, "count": 1, "self": 3.244699923999974 }, "TrainerController.advance": { "total": 2443.933636672015, "count": 63625, "self": 1.654925191050097, "children": { "env_step": { "total": 1710.9046968079656, "count": 63625, "self": 1532.2881324569491, "children": { "SubprocessEnvManager._take_step": { "total": 177.6585783690174, "count": 63625, "self": 5.351975674020309, "children": { "TorchPolicy.evaluate": { "total": 172.30660269499708, "count": 62572, "self": 172.30660269499708 } } }, "workers": { "total": 0.9579859819990588, "count": 63625, "self": 0.0, "children": { "worker_root": { "total": 2443.126842369968, "count": 63625, "is_parallel": true, "self": 1041.6887557779805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006266750000008869, "count": 1, "is_parallel": true, "self": 0.004704338000351527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015624119996573427, "count": 8, "is_parallel": true, "self": 0.0015624119996573427 } } }, "UnityEnvironment.step": { "total": 0.06719748900002287, "count": 1, "is_parallel": true, "self": 0.000636998000118183, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005791820000240477, "count": 1, "is_parallel": true, "self": 0.0005791820000240477 }, "communicator.exchange": { "total": 0.05666760099995827, "count": 1, "is_parallel": true, "self": 0.05666760099995827 }, "steps_from_proto": { "total": 0.009313707999922372, "count": 1, "is_parallel": true, "self": 0.007664094999881854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016496130000405174, "count": 8, "is_parallel": true, "self": 0.0016496130000405174 } } } } } } }, "UnityEnvironment.step": { "total": 1401.4380865919875, "count": 63624, "is_parallel": true, "self": 35.447663888977786, "children": { "UnityEnvironment._generate_step_input": { "total": 26.13110265003786, "count": 63624, "is_parallel": true, "self": 26.13110265003786 }, "communicator.exchange": { "total": 1229.5082169019938, "count": 63624, "is_parallel": true, "self": 1229.5082169019938 }, "steps_from_proto": { "total": 110.35110315097802, "count": 63624, "is_parallel": true, "self": 23.07206488892814, "children": { "_process_rank_one_or_two_observation": { "total": 87.27903826204988, "count": 508992, "is_parallel": true, "self": 87.27903826204988 } } } } } } } } } } }, "trainer_advance": { "total": 731.3740146729994, "count": 63625, "self": 3.002050928956578, "children": { "process_trajectory": { "total": 141.10566598804337, "count": 63625, "self": 140.7835109210431, "children": { "RLTrainer._checkpoint": { "total": 0.3221550670002671, "count": 2, "self": 0.3221550670002671 } } }, "_update_policy": { "total": 587.2662977559994, "count": 446, "self": 324.0806416729464, "children": { "TorchPPOOptimizer.update": { "total": 263.185656083053, "count": 22806, "self": 263.185656083053 } } } } } } }, "trainer_threads": { "total": 1.3300000318849925e-06, "count": 1, "self": 1.3300000318849925e-06 }, "TrainerController._save_models": { "total": 0.15699478900023678, "count": 1, "self": 0.002125228000295465, "children": { "RLTrainer._checkpoint": { "total": 0.1548695609999413, "count": 1, "self": 0.1548695609999413 } } } } } } }