{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37521347403526306, "min": 0.36693716049194336, "max": 1.4712775945663452, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11220.3837890625, "min": 11119.6640625, "max": 44632.67578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7008219957351685, "min": -0.11797916889190674, "max": 0.7192474007606506, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.23837280273438, "min": -28.432979583740234, "max": 207.5098114013672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016824286431074142, "min": -0.022372625768184662, "max": 0.1762920767068863, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.879043102264404, "min": -6.130099296569824, "max": 42.48638916015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06935427494352639, "min": 0.06620572407107737, "max": 0.07411827280794933, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9709598492093694, "min": 0.4878644189284177, "max": 1.0581663122672276, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013820216292515397, "min": 0.0007203140909728926, "max": 0.01666263421695873, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19348302809521556, "min": 0.008643769091674712, "max": 0.24795924529704885, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5524260539857145e-06, "min": 7.5524260539857145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001057339647558, "min": 0.0001057339647558, "max": 0.003632654289115299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251744285714284, "min": 0.10251744285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352441999999999, "min": 1.3886848, "max": 2.6108847, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002614925414285715, "min": 0.0002614925414285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003660895580000001, "min": 0.003660895580000001, "max": 0.12110738152999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009786483831703663, "min": 0.009786483831703663, "max": 0.3853275775909424, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13701076805591583, "min": 0.13701076805591583, "max": 2.6972930431365967, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.037037037037, "min": 255.4695652173913, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29488.0, "min": 15984.0, "max": 32292.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6733559479407214, "min": -1.0000000521540642, "max": 1.7404396381100704, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 182.39579832553864, "min": -30.322801634669304, "max": 201.89099802076817, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6733559479407214, "min": -1.0000000521540642, "max": 1.7404396381100704, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 182.39579832553864, "min": -30.322801634669304, "max": 201.89099802076817, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028104824934583564, "min": 0.026106195667955984, "max": 7.89645841345191, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0634259178696084, "min": 3.002212501814938, "max": 126.34333461523056, "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": "1706263057", "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 Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706265475" }, "total": 2418.5291520540004, "count": 1, "self": 0.4937112890006574, "children": { "run_training.setup": { "total": 0.052030088000265096, "count": 1, "self": 0.052030088000265096 }, "TrainerController.start_learning": { "total": 2417.9834106769995, "count": 1, "self": 1.825907090124474, "children": { "TrainerController._reset_env": { "total": 2.0745065450000766, "count": 1, "self": 2.0745065450000766 }, "TrainerController.advance": { "total": 2413.991288580875, "count": 64248, "self": 1.9445191926961343, "children": { "env_step": { "total": 1763.7244095521964, "count": 64248, "self": 1610.373990484085, "children": { "SubprocessEnvManager._take_step": { "total": 152.22948918414022, "count": 64248, "self": 5.661690075173283, "children": { "TorchPolicy.evaluate": { "total": 146.56779910896694, "count": 62560, "self": 146.56779910896694 } } }, "workers": { "total": 1.1209298839712574, "count": 64248, "self": 0.0, "children": { "worker_root": { "total": 2411.8606322089618, "count": 64248, "is_parallel": true, "self": 940.4462911188457, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018126790000678739, "count": 1, "is_parallel": true, "self": 0.0005416140002125758, "children": { "_process_rank_one_or_two_observation": { "total": 0.001271064999855298, "count": 8, "is_parallel": true, "self": 0.001271064999855298 } } }, "UnityEnvironment.step": { "total": 0.05332142399993245, "count": 1, "is_parallel": true, "self": 0.0006225530000847357, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048462999984622, "count": 1, "is_parallel": true, "self": 0.00048462999984622 }, "communicator.exchange": { "total": 0.05032278899989251, "count": 1, "is_parallel": true, "self": 0.05032278899989251 }, "steps_from_proto": { "total": 0.001891452000108984, "count": 1, "is_parallel": true, "self": 0.0003878540001096553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015035979999993287, "count": 8, "is_parallel": true, "self": 0.0015035979999993287 } } } } } } }, "UnityEnvironment.step": { "total": 1471.414341090116, "count": 64247, "is_parallel": true, "self": 38.449438196089886, "children": { "UnityEnvironment._generate_step_input": { "total": 27.813824333921275, "count": 64247, "is_parallel": true, "self": 27.813824333921275 }, "communicator.exchange": { "total": 1290.9877652590562, "count": 64247, "is_parallel": true, "self": 1290.9877652590562 }, "steps_from_proto": { "total": 114.16331330104867, "count": 64247, "is_parallel": true, "self": 24.35430929709719, "children": { "_process_rank_one_or_two_observation": { "total": 89.80900400395149, "count": 513976, "is_parallel": true, "self": 89.80900400395149 } } } } } } } } } } }, "trainer_advance": { "total": 648.3223598359823, "count": 64248, "self": 3.2962348980208844, "children": { "process_trajectory": { "total": 136.8373864219502, "count": 64248, "self": 136.6399273169509, "children": { "RLTrainer._checkpoint": { "total": 0.19745910499932506, "count": 2, "self": 0.19745910499932506 } } }, "_update_policy": { "total": 508.1887385160112, "count": 455, "self": 298.6700501180212, "children": { "TorchPPOOptimizer.update": { "total": 209.51868839799, "count": 22833, "self": 209.51868839799 } } } } } } }, "trainer_threads": { "total": 9.96999915514607e-07, "count": 1, "self": 9.96999915514607e-07 }, "TrainerController._save_models": { "total": 0.0917074640001374, "count": 1, "self": 0.001428682000550907, "children": { "RLTrainer._checkpoint": { "total": 0.0902787819995865, "count": 1, "self": 0.0902787819995865 } } } } } } }