{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7272578477859497, "min": 0.7272578477859497, "max": 1.5099250078201294, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21724.646484375, "min": 21724.646484375, "max": 45805.0859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1754050850868225, "min": -0.1359606385231018, "max": 0.20410382747650146, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 44.20207977294922, "min": -32.22267150878906, "max": 51.84237289428711, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03331143036484718, "min": -0.01020742580294609, "max": 0.5953606367111206, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.39448070526123, "min": -2.5722713470458984, "max": 141.1004638671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06745935281176453, "min": 0.06371140329777251, "max": 0.07553063341476537, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9444309393647035, "min": 0.48709898480433633, "max": 1.0568788443114518, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011153117247957589, "min": 0.00042332150834019334, "max": 0.01213410708870095, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15614364147140625, "min": 0.0029632505583813535, "max": 0.18201160633051425, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.312318991164286e-06, "min": 7.312318991164286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001023724658763, "min": 0.0001023724658763, "max": 0.0030202961932347004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243740714285712, "min": 0.10243740714285712, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341236999999998, "min": 1.327104, "max": 2.4004203, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025349697357142863, "min": 0.00025349697357142863, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003548957630000001, "min": 0.003548957630000001, "max": 0.10070585347, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01241157203912735, "min": 0.01241157203912735, "max": 0.529943585395813, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1737620085477829, "min": 0.1737620085477829, "max": 3.7096052169799805, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 637.6136363636364, "min": 637.6136363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28055.0, "min": 15984.0, "max": 33272.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7411644082930353, "min": -1.0000000521540642, "max": 0.8828849725425243, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 33.35239837318659, "min": -32.000001668930054, "max": 38.341598488390446, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7411644082930353, "min": -1.0000000521540642, "max": 0.8828849725425243, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 33.35239837318659, "min": -32.000001668930054, "max": 38.341598488390446, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08368938740653296, "min": 0.08368938740653296, "max": 11.420991665683687, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7660224332939833, "min": 3.7660224332939833, "max": 182.735866650939, "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": "1679155991", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679157933" }, "total": 1942.2473640980002, "count": 1, "self": 0.9961418979996779, "children": { "run_training.setup": { "total": 0.16160463200003505, "count": 1, "self": 0.16160463200003505 }, "TrainerController.start_learning": { "total": 1941.0896175680004, "count": 1, "self": 1.196706064945829, "children": { "TrainerController._reset_env": { "total": 7.02245062799966, "count": 1, "self": 7.02245062799966 }, "TrainerController.advance": { "total": 1932.731715456055, "count": 63233, "self": 1.3036401761128218, "children": { "env_step": { "total": 1318.656403348954, "count": 63233, "self": 1215.7399096991717, "children": { "SubprocessEnvManager._take_step": { "total": 102.17961731979358, "count": 63233, "self": 4.4584827627886625, "children": { "TorchPolicy.evaluate": { "total": 97.72113455700492, "count": 62555, "self": 97.72113455700492 } } }, "workers": { "total": 0.7368763299887178, "count": 63233, "self": 0.0, "children": { "worker_root": { "total": 1936.9862124009642, "count": 63233, "is_parallel": true, "self": 827.2685419969548, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023302650001824077, "count": 1, "is_parallel": true, "self": 0.0006678030003968161, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016624619997855916, "count": 8, "is_parallel": true, "self": 0.0016624619997855916 } } }, "UnityEnvironment.step": { "total": 0.04912288500008799, "count": 1, "is_parallel": true, "self": 0.0005037030005041743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004399760000524111, "count": 1, "is_parallel": true, "self": 0.0004399760000524111 }, "communicator.exchange": { "total": 0.04659470999968107, "count": 1, "is_parallel": true, "self": 0.04659470999968107 }, "steps_from_proto": { "total": 0.0015844959998503327, "count": 1, "is_parallel": true, "self": 0.00036956900021323236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012149269996371004, "count": 8, "is_parallel": true, "self": 0.0012149269996371004 } } } } } } }, "UnityEnvironment.step": { "total": 1109.7176704040094, "count": 63232, "is_parallel": true, "self": 29.79997984609645, "children": { "UnityEnvironment._generate_step_input": { "total": 21.985172875888566, "count": 63232, "is_parallel": true, "self": 21.985172875888566 }, "communicator.exchange": { "total": 970.4203381490165, "count": 63232, "is_parallel": true, "self": 970.4203381490165 }, "steps_from_proto": { "total": 87.51217953300784, "count": 63232, "is_parallel": true, "self": 18.241446458036535, "children": { "_process_rank_one_or_two_observation": { "total": 69.2707330749713, "count": 505856, "is_parallel": true, "self": 69.2707330749713 } } } } } } } } } } }, "trainer_advance": { "total": 612.7716719309883, "count": 63233, "self": 2.18822980890036, "children": { "process_trajectory": { "total": 110.13339912408037, "count": 63233, "self": 109.88893430308099, "children": { "RLTrainer._checkpoint": { "total": 0.24446482099938294, "count": 2, "self": 0.24446482099938294 } } }, "_update_policy": { "total": 500.4500429980076, "count": 429, "self": 320.0721611919821, "children": { "TorchPPOOptimizer.update": { "total": 180.37788180602547, "count": 22830, "self": 180.37788180602547 } } } } } } }, "trainer_threads": { "total": 1.4919996829121374e-06, "count": 1, "self": 1.4919996829121374e-06 }, "TrainerController._save_models": { "total": 0.1387439270001778, "count": 1, "self": 0.001936402999490383, "children": { "RLTrainer._checkpoint": { "total": 0.1368075240006874, "count": 1, "self": 0.1368075240006874 } } } } } } }