{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4259197413921356, "min": 0.42282000184059143, "max": 1.4124114513397217, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12770.77734375, "min": 12610.18359375, "max": 42846.9140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5083785653114319, "min": -0.10223829001188278, "max": 0.552173912525177, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.80410766601562, "min": -24.537189483642578, "max": 151.8478240966797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 3.9468648433685303, "min": -0.10601665079593658, "max": 3.9468648433685303, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1085.3878173828125, "min": -28.306446075439453, "max": 1085.3878173828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0683952487176232, "min": 0.06504880400080722, "max": 0.07363198173934596, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9575334820467248, "min": 0.5154238721754217, "max": 1.0624227616690582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.806191961338394, "min": 0.00024626051272518007, "max": 0.806191961338394, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 11.286687458737516, "min": 0.0029551261527021606, "max": 11.418709978771703, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.406947531050001e-06, "min": 7.406947531050001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010369726543470001, "min": 0.00010369726543470001, "max": 0.0032601857132714997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246895, "min": 0.10246895, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345653, "min": 1.3886848, "max": 2.4015148, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000256648105, "min": 0.000256648105, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359307347, "min": 0.00359307347, "max": 0.10869417715000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013734688051044941, "min": 0.013734688051044941, "max": 0.49918538331985474, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19228562712669373, "min": 0.19228562712669373, "max": 3.494297742843628, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 383.7692307692308, "min": 345.8095238095238, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29934.0, "min": 15984.0, "max": 33160.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4855012764984912, "min": -1.0000000521540642, "max": 1.606557122653439, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.38359829038382, "min": -30.996801614761353, "max": 134.95079830288887, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4855012764984912, "min": -1.0000000521540642, "max": 1.606557122653439, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.38359829038382, "min": -30.996801614761353, "max": 134.95079830288887, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05548924813146269, "min": 0.052263484039853904, "max": 10.053378919139504, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.272672106122627, "min": 4.200495742683415, "max": 160.85406270623207, "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": "1777796115", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777798320" }, "total": 2204.897517585, "count": 1, "self": 0.5816629880000619, "children": { "run_training.setup": { "total": 0.024644072999990385, "count": 1, "self": 0.024644072999990385 }, "TrainerController.start_learning": { "total": 2204.2912105240002, "count": 1, "self": 1.3949101020157286, "children": { "TrainerController._reset_env": { "total": 3.2162877829998706, "count": 1, "self": 3.2162877829998706 }, "TrainerController.advance": { "total": 2199.5991895289844, "count": 63575, "self": 1.5031313219951699, "children": { "env_step": { "total": 1523.7134230119927, "count": 63575, "self": 1365.9438529318995, "children": { "SubprocessEnvManager._take_step": { "total": 156.93690459706727, "count": 63575, "self": 4.755840578066909, "children": { "TorchPolicy.evaluate": { "total": 152.18106401900036, "count": 62550, "self": 152.18106401900036 } } }, "workers": { "total": 0.8326654830259486, "count": 63575, "self": 0.0, "children": { "worker_root": { "total": 2197.8405982230292, "count": 63575, "is_parallel": true, "self": 951.9962860070991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004390362000094683, "count": 1, "is_parallel": true, "self": 0.0030962790003741247, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012940829997205583, "count": 8, "is_parallel": true, "self": 0.0012940829997205583 } } }, "UnityEnvironment.step": { "total": 0.09237108199999966, "count": 1, "is_parallel": true, "self": 0.0005383019999953831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005033909999383468, "count": 1, "is_parallel": true, "self": 0.0005033909999383468 }, "communicator.exchange": { "total": 0.086418612999978, "count": 1, "is_parallel": true, "self": 0.086418612999978 }, "steps_from_proto": { "total": 0.004910776000087935, "count": 1, "is_parallel": true, "self": 0.0004055040001276211, "children": { "_process_rank_one_or_two_observation": { "total": 0.004505271999960314, "count": 8, "is_parallel": true, "self": 0.004505271999960314 } } } } } } }, "UnityEnvironment.step": { "total": 1245.8443122159301, "count": 63574, "is_parallel": true, "self": 34.28481657103134, "children": { "UnityEnvironment._generate_step_input": { "total": 24.09437311900342, "count": 63574, "is_parallel": true, "self": 24.09437311900342 }, "communicator.exchange": { "total": 1076.2103626669193, "count": 63574, "is_parallel": true, "self": 1076.2103626669193 }, "steps_from_proto": { "total": 111.25475985897606, "count": 63574, "is_parallel": true, "self": 23.22573424081702, "children": { "_process_rank_one_or_two_observation": { "total": 88.02902561815904, "count": 508592, "is_parallel": true, "self": 88.02902561815904 } } } } } } } } } } }, "trainer_advance": { "total": 674.3826351949963, "count": 63575, "self": 2.537977381976134, "children": { "process_trajectory": { "total": 128.41454571601616, "count": 63575, "self": 128.20470247801632, "children": { "RLTrainer._checkpoint": { "total": 0.2098432379998485, "count": 2, "self": 0.2098432379998485 } } }, "_update_policy": { "total": 543.430112097004, "count": 446, "self": 300.15427470400095, "children": { "TorchPPOOptimizer.update": { "total": 243.27583739300303, "count": 22839, "self": 243.27583739300303 } } } } } } }, "trainer_threads": { "total": 1.0980002116411924e-06, "count": 1, "self": 1.0980002116411924e-06 }, "TrainerController._save_models": { "total": 0.0808220120002261, "count": 1, "self": 0.0010533270001360506, "children": { "RLTrainer._checkpoint": { "total": 0.07976868500009004, "count": 1, "self": 0.07976868500009004 } } } } } } }