{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41370806097984314, "min": 0.41334280371665955, "max": 1.4638464450836182, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12331.8095703125, "min": 12331.8095703125, "max": 44407.24609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29885.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29885.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5111998915672302, "min": -0.23498310148715973, "max": 0.5727452635765076, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.57997131347656, "min": -55.69099426269531, "max": 156.9322052001953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04854857549071312, "min": -0.04854857549071312, "max": 0.4158308207988739, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.350858688354492, "min": -13.350858688354492, "max": 98.5519027709961, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06957268726962088, "min": 0.06354936105876617, "max": 0.07352809118534803, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9740176217746922, "min": 0.49911052818897167, "max": 1.0835417874948368, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014367856263388172, "min": 0.0007121789189315301, "max": 0.016933461969921494, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20114998768743442, "min": 0.009258325946109891, "max": 0.2373389502563263, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.71217600073571e-06, "min": 7.71217600073571e-06, "max": 0.0002952357873023571, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010797046401029995, "min": 0.00010797046401029995, "max": 0.0035085749304750993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257069285714289, "min": 0.10257069285714289, "max": 0.19841192857142856, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359897000000004, "min": 1.3888835, "max": 2.5695249000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026681221642857125, "min": 0.00026681221642857125, "max": 0.009841351664285713, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037353710299999976, "min": 0.0037353710299999976, "max": 0.11697553750999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00913336593657732, "min": 0.00913336593657732, "max": 0.41001421213150024, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12786711752414703, "min": 0.12786711752414703, "max": 2.8700995445251465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 373.5487804878049, "min": 314.75, "max": 995.4333333333333, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30631.0, "min": 16556.0, "max": 32940.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.57670118291694, "min": -0.9294933860500654, "max": 1.6460064284263118, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.86619818210602, "min": -30.472401708364487, "max": 153.078597843647, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.57670118291694, "min": -0.9294933860500654, "max": 1.6460064284263118, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.86619818210602, "min": -30.472401708364487, "max": 153.078597843647, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03594636857539067, "min": 0.031159100170235002, "max": 8.283276879612137, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.983548591757426, "min": 2.8363122256705537, "max": 140.81570695340633, "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": "1674738000", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674739969" }, "total": 1969.1885088840002, "count": 1, "self": 0.44174386200029403, "children": { "run_training.setup": { "total": 0.10454727100000127, "count": 1, "self": 0.10454727100000127 }, "TrainerController.start_learning": { "total": 1968.6422177509999, "count": 1, "self": 1.1052008560498052, "children": { "TrainerController._reset_env": { "total": 9.173534883000002, "count": 1, "self": 9.173534883000002 }, "TrainerController.advance": { "total": 1958.27002326395, "count": 63901, "self": 1.2115270589724787, "children": { "env_step": { "total": 1317.7817815889857, "count": 63901, "self": 1219.1043766260586, "children": { "SubprocessEnvManager._take_step": { "total": 97.98573101494844, "count": 63901, "self": 4.0951137810136515, "children": { "TorchPolicy.evaluate": { "total": 93.89061723393479, "count": 62545, "self": 31.61314597092519, "children": { "TorchPolicy.sample_actions": { "total": 62.2774712630096, "count": 62545, "self": 62.2774712630096 } } } } }, "workers": { "total": 0.6916739479786429, "count": 63901, "self": 0.0, "children": { "worker_root": { "total": 1965.6533483040216, "count": 63901, "is_parallel": true, "self": 839.0815126929917, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00642566400006217, "count": 1, "is_parallel": true, "self": 0.003564641000593838, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028610229994683323, "count": 8, "is_parallel": true, "self": 0.0028610229994683323 } } }, "UnityEnvironment.step": { "total": 0.044897537999986525, "count": 1, "is_parallel": true, "self": 0.0004948369999056013, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004295960000035848, "count": 1, "is_parallel": true, "self": 0.0004295960000035848 }, "communicator.exchange": { "total": 0.042455083000049854, "count": 1, "is_parallel": true, "self": 0.042455083000049854 }, "steps_from_proto": { "total": 0.0015180220000274858, "count": 1, "is_parallel": true, "self": 0.0003815450002093712, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011364769998181146, "count": 8, "is_parallel": true, "self": 0.0011364769998181146 } } } } } } }, "UnityEnvironment.step": { "total": 1126.5718356110299, "count": 63900, "is_parallel": true, "self": 26.888699989865017, "children": { "UnityEnvironment._generate_step_input": { "total": 20.994278624016488, "count": 63900, "is_parallel": true, "self": 20.994278624016488 }, "communicator.exchange": { "total": 991.7026802990711, "count": 63900, "is_parallel": true, "self": 991.7026802990711 }, "steps_from_proto": { "total": 86.98617669807732, "count": 63900, "is_parallel": true, "self": 20.07324013594598, "children": { "_process_rank_one_or_two_observation": { "total": 66.91293656213134, "count": 511200, "is_parallel": true, "self": 66.91293656213134 } } } } } } } } } } }, "trainer_advance": { "total": 639.2767146159918, "count": 63901, "self": 2.289128296013587, "children": { "process_trajectory": { "total": 138.6425250229795, "count": 63901, "self": 138.46705489397937, "children": { "RLTrainer._checkpoint": { "total": 0.17547012900013215, "count": 2, "self": 0.17547012900013215 } } }, "_update_policy": { "total": 498.34506129699867, "count": 455, "self": 186.9210905640034, "children": { "TorchPPOOptimizer.update": { "total": 311.42397073299526, "count": 22797, "self": 311.42397073299526 } } } } } } }, "trainer_threads": { "total": 8.450001587334555e-07, "count": 1, "self": 8.450001587334555e-07 }, "TrainerController._save_models": { "total": 0.09345790299994405, "count": 1, "self": 0.0013481870000759955, "children": { "RLTrainer._checkpoint": { "total": 0.09210971599986806, "count": 1, "self": 0.09210971599986806 } } } } } } }