{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45466336607933044, "min": 0.44923412799835205, "max": 1.4188765287399292, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13588.978515625, "min": 13462.6484375, "max": 43043.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5463098287582397, "min": -0.09834287315607071, "max": 0.5608314871788025, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.5130615234375, "min": -23.6022891998291, "max": 156.47198486328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0026641248259693384, "min": -0.08801711350679398, "max": 0.3681930899620056, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7486190795898438, "min": -22.796432495117188, "max": 87.26176452636719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06760175410415671, "min": 0.06494110913763634, "max": 0.07287662190383538, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9464245574581939, "min": 0.5101363533268477, "max": 1.0680840688645747, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01774917179674591, "min": 0.00013236573603211626, "max": 0.01774917179674591, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24848840515444276, "min": 0.0014560230963532787, "max": 0.24848840515444276, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.243490442678569e-06, "min": 7.243490442678569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010140886619749997, "min": 0.00010140886619749997, "max": 0.003331815689394799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241446428571428, "min": 0.10241446428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338024999999999, "min": 1.3886848, "max": 2.4023023, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002512049821428571, "min": 0.0002512049821428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035168697499999993, "min": 0.0035168697499999993, "max": 0.11106945948000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010580264963209629, "min": 0.010538310743868351, "max": 0.46798253059387207, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14812371134757996, "min": 0.14812371134757996, "max": 3.2758777141571045, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 341.8588235294118, "min": 341.8588235294118, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29058.0, "min": 15984.0, "max": 33169.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.658141159485368, "min": -1.0000000521540642, "max": 1.658141159485368, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.9419985562563, "min": -31.998801678419113, "max": 140.9419985562563, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.658141159485368, "min": -1.0000000521540642, "max": 1.658141159485368, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.9419985562563, "min": -31.998801678419113, "max": 140.9419985562563, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037389465170802876, "min": 0.037389465170802876, "max": 9.211605932563543, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1781045395182446, "min": 3.1781045395182446, "max": 147.3856949210167, "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": "1711100833", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/dl/miniconda3/envs/huggydog/bin/mlagents-learn ./ml-agents/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": "1711102318" }, "total": 1484.8410472271498, "count": 1, "self": 0.320609939051792, "children": { "run_training.setup": { "total": 0.01576058496721089, "count": 1, "self": 0.01576058496721089 }, "TrainerController.start_learning": { "total": 1484.5046767031308, "count": 1, "self": 0.8179836231283844, "children": { "TrainerController._reset_env": { "total": 2.0840904898941517, "count": 1, "self": 2.0840904898941517 }, "TrainerController.advance": { "total": 1481.5450675270986, "count": 63581, "self": 0.7812007474713027, "children": { "env_step": { "total": 1036.6117768012919, "count": 63581, "self": 959.3268416887149, "children": { "SubprocessEnvManager._take_step": { "total": 76.77315868809819, "count": 63581, "self": 2.8659987037535757, "children": { "TorchPolicy.evaluate": { "total": 73.90715998434462, "count": 62568, "self": 73.90715998434462 } } }, "workers": { "total": 0.5117764244787395, "count": 63581, "self": 0.0, "children": { "worker_root": { "total": 1482.5885681076907, "count": 63581, "is_parallel": true, "self": 607.7412814889103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036372230388224125, "count": 1, "is_parallel": true, "self": 0.0010787250939756632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025584979448467493, "count": 8, "is_parallel": true, "self": 0.0025584979448467493 } } }, "UnityEnvironment.step": { "total": 0.036101788049563766, "count": 1, "is_parallel": true, "self": 0.0003568923566490412, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005851138848811388, "count": 1, "is_parallel": true, "self": 0.0005851138848811388 }, "communicator.exchange": { "total": 0.03422658098861575, "count": 1, "is_parallel": true, "self": 0.03422658098861575 }, "steps_from_proto": { "total": 0.0009332008194178343, "count": 1, "is_parallel": true, "self": 0.00023260083980858326, "children": { "_process_rank_one_or_two_observation": { "total": 0.000700599979609251, "count": 8, "is_parallel": true, "self": 0.000700599979609251 } } } } } } }, "UnityEnvironment.step": { "total": 874.8472866187803, "count": 63580, "is_parallel": true, "self": 23.37540243868716, "children": { "UnityEnvironment._generate_step_input": { "total": 16.354067062027752, "count": 63580, "is_parallel": true, "self": 16.354067062027752 }, "communicator.exchange": { "total": 768.3595404627267, "count": 63580, "is_parallel": true, "self": 768.3595404627267 }, "steps_from_proto": { "total": 66.7582766553387, "count": 63580, "is_parallel": true, "self": 13.979746239958331, "children": { "_process_rank_one_or_two_observation": { "total": 52.778530415380374, "count": 508640, "is_parallel": true, "self": 52.778530415380374 } } } } } } } } } } }, "trainer_advance": { "total": 444.1520899783354, "count": 63581, "self": 1.9876580825075507, "children": { "process_trajectory": { "total": 79.12721569859423, "count": 63581, "self": 78.99438175046816, "children": { "RLTrainer._checkpoint": { "total": 0.13283394812606275, "count": 2, "self": 0.13283394812606275 } } }, "_update_policy": { "total": 363.03721619723365, "count": 444, "self": 196.6466749124229, "children": { "TorchPPOOptimizer.update": { "total": 166.39054128481075, "count": 22836, "self": 166.39054128481075 } } } } } } }, "trainer_threads": { "total": 7.199123501777649e-07, "count": 1, "self": 7.199123501777649e-07 }, "TrainerController._save_models": { "total": 0.05753434309735894, "count": 1, "self": 0.0009075752459466457, "children": { "RLTrainer._checkpoint": { "total": 0.056626767851412296, "count": 1, "self": 0.056626767851412296 } } } } } } }