{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4084797203540802, "min": 0.4013776183128357, "max": 1.4468796253204346, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12306.6767578125, "min": 12086.283203125, "max": 43892.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29933.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29933.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5081204771995544, "min": -0.09900214523077011, "max": 0.5792565941810608, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.71688842773438, "min": -23.760515213012695, "max": 157.55780029296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011207140050828457, "min": 0.00031018207664601505, "max": 0.26933401823043823, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.059549331665039, "min": 0.08436952531337738, "max": 64.64016723632812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06612420288729481, "min": 0.06480215453704675, "max": 0.0750653944348619, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9257388404221274, "min": 0.5254577610440333, "max": 1.1061366223342095, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014967264050764718, "min": 0.00042045791762631917, "max": 0.016697437729302846, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20954169671070605, "min": 0.0042045791762631915, "max": 0.23376412821023987, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.648576021935717e-06, "min": 7.648576021935717e-06, "max": 0.0002952337301601857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010708006430710002, "min": 0.00010708006430710002, "max": 0.0032559677146774997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254949285714285, "min": 0.10254949285714285, "max": 0.19841124285714287, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356928999999998, "min": 1.3888787, "max": 2.5722991000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002646943364285715, "min": 0.0002646943364285715, "max": 0.009841283161428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003705720710000001, "min": 0.003705720710000001, "max": 0.10855371775, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010171957314014435, "min": 0.009861755184829235, "max": 0.4606410562992096, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1424074023962021, "min": 0.13806457817554474, "max": 3.2244873046875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 364.01234567901236, "min": 345.6024096385542, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29485.0, "min": 16732.0, "max": 33516.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5371826994750235, "min": -0.9999742455059483, "max": 1.6525595099443482, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.5117986574769, "min": -31.998401656746864, "max": 138.81499883532524, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5371826994750235, "min": -0.9999742455059483, "max": 1.6525595099443482, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.5117986574769, "min": -31.998401656746864, "max": 138.81499883532524, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038311669484778293, "min": 0.037454483196294554, "max": 8.736794147421332, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.103245228267042, "min": 3.0550482180551626, "max": 148.52550050616264, "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": "1708878852", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708880912" }, "total": 2059.795728152, "count": 1, "self": 0.5386451989998022, "children": { "run_training.setup": { "total": 0.04644038699962039, "count": 1, "self": 0.04644038699962039 }, "TrainerController.start_learning": { "total": 2059.2106425660004, "count": 1, "self": 1.1940370690308555, "children": { "TrainerController._reset_env": { "total": 2.41643457400005, "count": 1, "self": 2.41643457400005 }, "TrainerController.advance": { "total": 2055.51728907497, "count": 63719, "self": 1.2848705309156685, "children": { "env_step": { "total": 1452.828058919999, "count": 63719, "self": 1331.2349123449694, "children": { "SubprocessEnvManager._take_step": { "total": 120.84432641208787, "count": 63719, "self": 4.514179355068791, "children": { "TorchPolicy.evaluate": { "total": 116.33014705701908, "count": 62562, "self": 116.33014705701908 } } }, "workers": { "total": 0.7488201629416835, "count": 63719, "self": 0.0, "children": { "worker_root": { "total": 2054.607269856051, "count": 63719, "is_parallel": true, "self": 830.1912026740965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021215060000940866, "count": 1, "is_parallel": true, "self": 0.0006587680004486174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014627379996454692, "count": 8, "is_parallel": true, "self": 0.0014627379996454692 } } }, "UnityEnvironment.step": { "total": 0.04814428500003487, "count": 1, "is_parallel": true, "self": 0.0005750300006184261, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005009449996578041, "count": 1, "is_parallel": true, "self": 0.0005009449996578041 }, "communicator.exchange": { "total": 0.04542311499972129, "count": 1, "is_parallel": true, "self": 0.04542311499972129 }, "steps_from_proto": { "total": 0.0016451950000373472, "count": 1, "is_parallel": true, "self": 0.0003696210010275536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012755739990097936, "count": 8, "is_parallel": true, "self": 0.0012755739990097936 } } } } } } }, "UnityEnvironment.step": { "total": 1224.4160671819545, "count": 63718, "is_parallel": true, "self": 33.64134723086909, "children": { "UnityEnvironment._generate_step_input": { "total": 23.47814460501786, "count": 63718, "is_parallel": true, "self": 23.47814460501786 }, "communicator.exchange": { "total": 1072.6278001810106, "count": 63718, "is_parallel": true, "self": 1072.6278001810106 }, "steps_from_proto": { "total": 94.66877516505701, "count": 63718, "is_parallel": true, "self": 18.26925913601508, "children": { "_process_rank_one_or_two_observation": { "total": 76.39951602904193, "count": 509744, "is_parallel": true, "self": 76.39951602904193 } } } } } } } } } } }, "trainer_advance": { "total": 601.4043596240554, "count": 63719, "self": 2.3839150220483134, "children": { "process_trajectory": { "total": 119.10497887800284, "count": 63719, "self": 118.91675165600327, "children": { "RLTrainer._checkpoint": { "total": 0.18822722199956843, "count": 2, "self": 0.18822722199956843 } } }, "_update_policy": { "total": 479.9154657240042, "count": 448, "self": 284.21174350003, "children": { "TorchPPOOptimizer.update": { "total": 195.70372222397418, "count": 22746, "self": 195.70372222397418 } } } } } } }, "trainer_threads": { "total": 1.0129997463081963e-06, "count": 1, "self": 1.0129997463081963e-06 }, "TrainerController._save_models": { "total": 0.08288083499974164, "count": 1, "self": 0.0014182699997036252, "children": { "RLTrainer._checkpoint": { "total": 0.08146256500003801, "count": 1, "self": 0.08146256500003801 } } } } } } }