{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21302199363708496, "min": 0.21302199363708496, "max": 1.4299259185791016, "count": 58 }, "Pyramids.Policy.Entropy.sum": { "value": 6373.6181640625, "min": 6373.6181640625, "max": 43378.234375, "count": 58 }, "Pyramids.Step.mean": { "value": 1739906.0, "min": 29952.0, "max": 1739906.0, "count": 58 }, "Pyramids.Step.sum": { "value": 1739906.0, "min": 29952.0, "max": 1739906.0, "count": 58 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7808756232261658, "min": -0.09550435841083527, "max": 0.8141438961029053, "count": 58 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 229.5774383544922, "min": -23.1120548248291, "max": 245.05731201171875, "count": 58 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017437996342778206, "min": -0.004383192863315344, "max": 0.4441741704940796, "count": 58 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.126770973205566, "min": -1.1264805793762207, "max": 105.26927947998047, "count": 58 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07112395247664297, "min": 0.0644080444894609, "max": 0.07578669143203157, "count": 58 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9957353346730016, "min": 0.49415558890185995, "max": 1.061013680048442, "count": 58 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012997365766090757, "min": 0.0002416005040601366, "max": 0.018060553580613082, "count": 58 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1819631207252706, "min": 0.003140806552781776, "max": 0.2709083037091962, "count": 58 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00012755035034037857, "min": 0.00012755035034037857, "max": 0.00029838354339596195, "count": 58 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0017857049047653, "min": 0.0017857049047653, "max": 0.004010039263320266, "count": 58 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14251676428571428, "min": 0.14251676428571428, "max": 0.19946118095238097, "count": 58 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.9952347, "min": 1.3962282666666668, "max": 2.797474566666667, "count": 58 }, "Pyramids.Policy.Beta.mean": { "value": 0.004257424752142857, "min": 0.004257424752142857, "max": 0.009946171977142856, "count": 58 }, "Pyramids.Policy.Beta.sum": { "value": 0.05960394653, "min": 0.05960394653, "max": 0.13367430536, "count": 58 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010542534291744232, "min": 0.010323203168809414, "max": 0.43151411414146423, "count": 58 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14759548008441925, "min": 0.14452484250068665, "max": 3.020598888397217, "count": 58 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 264.7583333333333, "min": 229.125, "max": 999.0, "count": 58 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31771.0, "min": 15984.0, "max": 33512.0, "count": 58 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.685218318675955, "min": -1.0000000521540642, "max": 1.7708749865414575, "count": 58 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.22619824111462, "min": -30.993001624941826, "max": 227.5271983295679, "count": 58 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.685218318675955, "min": -1.0000000521540642, "max": 1.7708749865414575, "count": 58 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.22619824111462, "min": -30.993001624941826, "max": 227.5271983295679, "count": 58 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028383254223081168, "min": 0.026404364296467975, "max": 8.6148909535259, "count": 58 }, "Pyramids.Policy.RndReward.sum": { "value": 3.40599050676974, "min": 3.1642717106224154, "max": 137.8382552564144, "count": 58 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 58 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 58 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707534601", "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": "1707538726" }, "total": 4125.246884005, "count": 1, "self": 0.4197832119998566, "children": { "run_training.setup": { "total": 0.053459410999948886, "count": 1, "self": 0.053459410999948886 }, "TrainerController.start_learning": { "total": 4124.773641382, "count": 1, "self": 2.3762352360690784, "children": { "TrainerController._reset_env": { "total": 2.9119080120003673, "count": 1, "self": 2.9119080120003673 }, "TrainerController.advance": { "total": 4119.336418957931, "count": 114232, "self": 2.5098101548437626, "children": { "env_step": { "total": 2994.0612274481214, "count": 114232, "self": 2765.8155450451995, "children": { "SubprocessEnvManager._take_step": { "total": 226.817101242048, "count": 114232, "self": 8.190596317003383, "children": { "TorchPolicy.evaluate": { "total": 218.62650492504463, "count": 110497, "self": 218.62650492504463 } } }, "workers": { "total": 1.4285811608738186, "count": 114231, "self": 0.0, "children": { "worker_root": { "total": 4115.741242391978, "count": 114231, "is_parallel": true, "self": 1552.5245138059254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020951250003236055, "count": 1, "is_parallel": true, "self": 0.0006537070003105327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014414180000130727, "count": 8, "is_parallel": true, "self": 0.0014414180000130727 } } }, "UnityEnvironment.step": { "total": 0.06068620699988969, "count": 1, "is_parallel": true, "self": 0.0005797749995508639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004186720002508082, "count": 1, "is_parallel": true, "self": 0.0004186720002508082 }, "communicator.exchange": { "total": 0.05810506199986776, "count": 1, "is_parallel": true, "self": 0.05810506199986776 }, "steps_from_proto": { "total": 0.0015826980002202617, "count": 1, "is_parallel": true, "self": 0.0003617320003286295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012209659998916322, "count": 8, "is_parallel": true, "self": 0.0012209659998916322 } } } } } } }, "UnityEnvironment.step": { "total": 2563.2167285860523, "count": 114230, "is_parallel": true, "self": 62.629328094092216, "children": { "UnityEnvironment._generate_step_input": { "total": 43.972513573908145, "count": 114230, "is_parallel": true, "self": 43.972513573908145 }, "communicator.exchange": { "total": 2280.2044378101, "count": 114230, "is_parallel": true, "self": 2280.2044378101 }, "steps_from_proto": { "total": 176.410449107952, "count": 114230, "is_parallel": true, "self": 35.051696968574106, "children": { "_process_rank_one_or_two_observation": { "total": 141.35875213937788, "count": 913840, "is_parallel": true, "self": 141.35875213937788 } } } } } } } } } } }, "trainer_advance": { "total": 1122.765381354965, "count": 114231, "self": 4.781512252900484, "children": { "process_trajectory": { "total": 226.88922172106504, "count": 114231, "self": 226.56816519306494, "children": { "RLTrainer._checkpoint": { "total": 0.3210565280000992, "count": 3, "self": 0.3210565280000992 } } }, "_update_policy": { "total": 891.0946473809995, "count": 821, "self": 520.5461531090036, "children": { "TorchPPOOptimizer.update": { "total": 370.5484942719959, "count": 40221, "self": 370.5484942719959 } } } } } } }, "trainer_threads": { "total": 1.6920002963161096e-06, "count": 1, "self": 1.6920002963161096e-06 }, "TrainerController._save_models": { "total": 0.14907748399946286, "count": 1, "self": 0.0019383039998501772, "children": { "RLTrainer._checkpoint": { "total": 0.14713917999961268, "count": 1, "self": 0.14713917999961268 } } } } } } }