{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3847190737724304, "min": 0.3847190737724304, "max": 1.4579434394836426, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11480.017578125, "min": 11480.017578125, "max": 44228.171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4826076030731201, "min": -0.13756997883319855, "max": 0.4826076030731201, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.82144165039062, "min": -33.15436553955078, "max": 129.82144165039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17355215549468994, "min": -0.015009300783276558, "max": 0.3037053942680359, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 46.68553161621094, "min": -3.6472601890563965, "max": 71.97817993164062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06689880081380362, "min": 0.06429246715250961, "max": 0.07291757785650486, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9365832113932506, "min": 0.5024162245131213, "max": 1.093763667847573, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01711154147085922, "min": 0.0001484358197053276, "max": 0.01711154147085922, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2395615805920291, "min": 0.0019296656561692588, "max": 0.2395615805920291, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.35620469082143e-06, "min": 7.35620469082143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010298686567150003, "min": 0.00010298686567150003, "max": 0.0033729115756961996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245203571428571, "min": 0.10245203571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343285, "min": 1.3886848, "max": 2.4844058, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000254958367857143, "min": 0.000254958367857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035694171500000016, "min": 0.0035694171500000016, "max": 0.11244794962, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009604391641914845, "min": 0.009522798471152782, "max": 0.3274954855442047, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13446147739887238, "min": 0.1333191841840744, "max": 2.292468309402466, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 385.8125, "min": 385.8125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30865.0, "min": 15984.0, "max": 32879.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4391224784776568, "min": -1.0000000521540642, "max": 1.4844738136117275, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.12979827821255, "min": -31.994001641869545, "max": 115.12979827821255, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4391224784776568, "min": -1.0000000521540642, "max": 1.4844738136117275, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.12979827821255, "min": -31.994001641869545, "max": 115.12979827821255, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03816621779405978, "min": 0.03816621779405978, "max": 6.66554023232311, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.053297423524782, "min": 2.825354659995355, "max": 106.64864371716976, "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": "1724963017", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724966108" }, "total": 3091.3470665470004, "count": 1, "self": 0.5977128700005778, "children": { "run_training.setup": { "total": 0.07369486300012795, "count": 1, "self": 0.07369486300012795 }, "TrainerController.start_learning": { "total": 3090.6756588139997, "count": 1, "self": 2.3854538019486426, "children": { "TrainerController._reset_env": { "total": 2.4462970460001543, "count": 1, "self": 2.4462970460001543 }, "TrainerController.advance": { "total": 3085.7644295180503, "count": 63530, "self": 2.6616582940418994, "children": { "env_step": { "total": 2053.867759884066, "count": 63530, "self": 1895.7720468780778, "children": { "SubprocessEnvManager._take_step": { "total": 156.6470868500121, "count": 63530, "self": 6.755808780073039, "children": { "TorchPolicy.evaluate": { "total": 149.89127806993906, "count": 62545, "self": 149.89127806993906 } } }, "workers": { "total": 1.4486261559759441, "count": 63530, "self": 0.0, "children": { "worker_root": { "total": 3083.687079837029, "count": 63530, "is_parallel": true, "self": 1370.1021062061027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034762039999804983, "count": 1, "is_parallel": true, "self": 0.0012536989997897763, "children": { "_process_rank_one_or_two_observation": { "total": 0.002222505000190722, "count": 8, "is_parallel": true, "self": 0.002222505000190722 } } }, "UnityEnvironment.step": { "total": 0.06373096900006203, "count": 1, "is_parallel": true, "self": 0.0007944429999042768, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005405209999480576, "count": 1, "is_parallel": true, "self": 0.0005405209999480576 }, "communicator.exchange": { "total": 0.060433757000055266, "count": 1, "is_parallel": true, "self": 0.060433757000055266 }, "steps_from_proto": { "total": 0.001962248000154432, "count": 1, "is_parallel": true, "self": 0.0004268540001248766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015353940000295552, "count": 8, "is_parallel": true, "self": 0.0015353940000295552 } } } } } } }, "UnityEnvironment.step": { "total": 1713.5849736309265, "count": 63529, "is_parallel": true, "self": 48.332891162092665, "children": { "UnityEnvironment._generate_step_input": { "total": 30.306188719927604, "count": 63529, "is_parallel": true, "self": 30.306188719927604 }, "communicator.exchange": { "total": 1508.4459509659885, "count": 63529, "is_parallel": true, "self": 1508.4459509659885 }, "steps_from_proto": { "total": 126.49994278291774, "count": 63529, "is_parallel": true, "self": 26.867544633967782, "children": { "_process_rank_one_or_two_observation": { "total": 99.63239814894996, "count": 508232, "is_parallel": true, "self": 99.63239814894996 } } } } } } } } } } }, "trainer_advance": { "total": 1029.2350113399427, "count": 63530, "self": 4.314360312956751, "children": { "process_trajectory": { "total": 162.92691289798518, "count": 63530, "self": 162.7518638009849, "children": { "RLTrainer._checkpoint": { "total": 0.17504909700028293, "count": 2, "self": 0.17504909700028293 } } }, "_update_policy": { "total": 861.9937381290008, "count": 449, "self": 355.52732765303676, "children": { "TorchPPOOptimizer.update": { "total": 506.46641047596404, "count": 22779, "self": 506.46641047596404 } } } } } } }, "trainer_threads": { "total": 1.0630001270328648e-06, "count": 1, "self": 1.0630001270328648e-06 }, "TrainerController._save_models": { "total": 0.0794773850002457, "count": 1, "self": 0.0020265339999241405, "children": { "RLTrainer._checkpoint": { "total": 0.07745085100032156, "count": 1, "self": 0.07745085100032156 } } } } } } }