{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5453658103942871, "min": 0.5158137083053589, "max": 1.439046025276184, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16535.4921875, "min": 15523.9296875, "max": 43654.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29906.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29906.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32423487305641174, "min": -0.09445164352655411, "max": 0.39033785462379456, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.9768295288086, "min": -22.762845993041992, "max": 105.78155517578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.5737321376800537, "min": -0.5737321376800537, "max": 0.37789350748062134, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -148.59661865234375, "min": -148.59661865234375, "max": 89.56076049804688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06768697331092419, "min": 0.06470396542556578, "max": 0.07309188987918398, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9476176263529387, "min": 0.5105749503965289, "max": 1.0232864583085757, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.09397981162375381, "min": 0.0003160863271483464, "max": 0.09397981162375381, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.3157173627325534, "min": 0.00442520858007685, "max": 1.3157173627325534, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4190975269999965e-06, "min": 7.4190975269999965e-06, "max": 0.00029523488730265714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010386736537799995, "min": 0.00010386736537799995, "max": 0.0035080616306461996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247300000000002, "min": 0.10247300000000002, "max": 0.19841162857142858, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346220000000003, "min": 1.3888814, "max": 2.5693538, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025705269999999993, "min": 0.00025705269999999993, "max": 0.009841321694285714, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035987377999999993, "min": 0.0035987377999999993, "max": 0.11695844461999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0154758021235466, "min": 0.0154758021235466, "max": 0.5777316093444824, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2166612297296524, "min": 0.2166612297296524, "max": 4.044121265411377, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 497.73214285714283, "min": 491.8833333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27873.0, "min": 16705.0, "max": 34069.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2879321153408714, "min": -0.9996500505755345, "max": 1.341393306851387, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.1241984590888, "min": -30.438401721417904, "max": 82.61779855936766, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2879321153408714, "min": -0.9996500505755345, "max": 1.341393306851387, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.1241984590888, "min": -30.438401721417904, "max": 82.61779855936766, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07930375667638145, "min": 0.07930375667638145, "max": 10.823394605342079, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.441010373877361, "min": 4.441010373877361, "max": 183.99770829081535, "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": "1748251083", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748253231" }, "total": 2147.913380379, "count": 1, "self": 0.492301819000204, "children": { "run_training.setup": { "total": 0.019991762999779894, "count": 1, "self": 0.019991762999779894 }, "TrainerController.start_learning": { "total": 2147.401086797, "count": 1, "self": 1.4752297209856806, "children": { "TrainerController._reset_env": { "total": 2.4159580030000143, "count": 1, "self": 2.4159580030000143 }, "TrainerController.advance": { "total": 2143.4236585550143, "count": 63417, "self": 1.4785896650441828, "children": { "env_step": { "total": 1470.5314425209879, "count": 63417, "self": 1315.757239077967, "children": { "SubprocessEnvManager._take_step": { "total": 153.95902647995558, "count": 63417, "self": 4.780107610942878, "children": { "TorchPolicy.evaluate": { "total": 149.1789188690127, "count": 62566, "self": 149.1789188690127 } } }, "workers": { "total": 0.8151769630653689, "count": 63417, "self": 0.0, "children": { "worker_root": { "total": 2142.4128954580206, "count": 63417, "is_parallel": true, "self": 941.9731849789766, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001987517999850752, "count": 1, "is_parallel": true, "self": 0.0006733169991548493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013142010006959026, "count": 8, "is_parallel": true, "self": 0.0013142010006959026 } } }, "UnityEnvironment.step": { "total": 0.07972014500001023, "count": 1, "is_parallel": true, "self": 0.0005425279998689803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004988659998161893, "count": 1, "is_parallel": true, "self": 0.0004988659998161893 }, "communicator.exchange": { "total": 0.07707876400013447, "count": 1, "is_parallel": true, "self": 0.07707876400013447 }, "steps_from_proto": { "total": 0.0015999870001905947, "count": 1, "is_parallel": true, "self": 0.0003472390003480541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012527479998425406, "count": 8, "is_parallel": true, "self": 0.0012527479998425406 } } } } } } }, "UnityEnvironment.step": { "total": 1200.439710479044, "count": 63416, "is_parallel": true, "self": 31.949928704976855, "children": { "UnityEnvironment._generate_step_input": { "total": 23.05653361103532, "count": 63416, "is_parallel": true, "self": 23.05653361103532 }, "communicator.exchange": { "total": 1048.716164739022, "count": 63416, "is_parallel": true, "self": 1048.716164739022 }, "steps_from_proto": { "total": 96.71708342400984, "count": 63416, "is_parallel": true, "self": 19.872896510889632, "children": { "_process_rank_one_or_two_observation": { "total": 76.84418691312021, "count": 507328, "is_parallel": true, "self": 76.84418691312021 } } } } } } } } } } }, "trainer_advance": { "total": 671.4136263689822, "count": 63417, "self": 2.7205888679529835, "children": { "process_trajectory": { "total": 130.18905950102862, "count": 63417, "self": 129.98963001802895, "children": { "RLTrainer._checkpoint": { "total": 0.1994294829996761, "count": 2, "self": 0.1994294829996761 } } }, "_update_policy": { "total": 538.5039780000006, "count": 451, "self": 299.2034591139902, "children": { "TorchPPOOptimizer.update": { "total": 239.30051888601042, "count": 22782, "self": 239.30051888601042 } } } } } } }, "trainer_threads": { "total": 1.2669997886405326e-06, "count": 1, "self": 1.2669997886405326e-06 }, "TrainerController._save_models": { "total": 0.08623925100027918, "count": 1, "self": 0.0018241950001538498, "children": { "RLTrainer._checkpoint": { "total": 0.08441505600012533, "count": 1, "self": 0.08441505600012533 } } } } } } }