{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3152073323726654, "min": 0.3152073323726654, "max": 1.4601354598999023, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9481.4365234375, "min": 9481.4365234375, "max": 44294.66796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.647743821144104, "min": -0.10171780735254288, "max": 0.6624165773391724, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.66375732421875, "min": -24.513992309570312, "max": 190.11355590820312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010502557270228863, "min": -0.012149021029472351, "max": 0.5516899824142456, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.961721181869507, "min": -3.4624710083007812, "max": 130.75051879882812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07069372382067654, "min": 0.06508259540229724, "max": 0.0729023304139761, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9897121334894715, "min": 0.5103163128978327, "max": 1.0785730369389057, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01618822922838652, "min": 0.00018977277266174673, "max": 0.01630761934149882, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22663520919741129, "min": 0.0024670460446027075, "max": 0.2361037635273533, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.277626145585714e-06, "min": 7.277626145585714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010188676603819999, "min": 0.00010188676603819999, "max": 0.0036340501886499995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242584285714287, "min": 0.10242584285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339618000000003, "min": 1.3886848, "max": 2.61135, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002523417014285715, "min": 0.0002523417014285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003532783820000001, "min": 0.003532783820000001, "max": 0.12115386500000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013320938684046268, "min": 0.013320938684046268, "max": 0.5119308829307556, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1864931434392929, "min": 0.1864931434392929, "max": 3.5835161209106445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 289.7047619047619, "min": 285.5090909090909, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30419.0, "min": 15984.0, "max": 33394.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6150209340311232, "min": -1.0000000521540642, "max": 1.7086862616387068, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.57719807326794, "min": -30.994001612067223, "max": 182.59239774942398, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6150209340311232, "min": -1.0000000521540642, "max": 1.7086862616387068, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.57719807326794, "min": -30.994001612067223, "max": 182.59239774942398, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03966585698806392, "min": 0.03966585698806392, "max": 10.6147140879184, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.164914983746712, "min": 4.070482785347849, "max": 169.8354254066944, "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": "1694803910", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694806364" }, "total": 2454.175507601, "count": 1, "self": 0.5354874979998385, "children": { "run_training.setup": { "total": 0.04120493899995381, "count": 1, "self": 0.04120493899995381 }, "TrainerController.start_learning": { "total": 2453.598815164, "count": 1, "self": 1.7512706150928352, "children": { "TrainerController._reset_env": { "total": 4.578252930999952, "count": 1, "self": 4.578252930999952 }, "TrainerController.advance": { "total": 2447.1724631619077, "count": 64021, "self": 1.648729527078558, "children": { "env_step": { "total": 1765.0601682479148, "count": 64021, "self": 1640.146276301934, "children": { "SubprocessEnvManager._take_step": { "total": 123.86492587100679, "count": 64021, "self": 5.270563284961554, "children": { "TorchPolicy.evaluate": { "total": 118.59436258604524, "count": 62551, "self": 118.59436258604524 } } }, "workers": { "total": 1.0489660749740324, "count": 64021, "self": 0.0, "children": { "worker_root": { "total": 2447.6413237849865, "count": 64021, "is_parallel": true, "self": 936.3214993438567, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018201090001639386, "count": 1, "is_parallel": true, "self": 0.0005530180003461282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012670909998178104, "count": 8, "is_parallel": true, "self": 0.0012670909998178104 } } }, "UnityEnvironment.step": { "total": 0.08664351100014756, "count": 1, "is_parallel": true, "self": 0.0005824540000958223, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048001000004660455, "count": 1, "is_parallel": true, "self": 0.00048001000004660455 }, "communicator.exchange": { "total": 0.08268501399993511, "count": 1, "is_parallel": true, "self": 0.08268501399993511 }, "steps_from_proto": { "total": 0.0028960330000700196, "count": 1, "is_parallel": true, "self": 0.0003693729995575268, "children": { "_process_rank_one_or_two_observation": { "total": 0.002526660000512493, "count": 8, "is_parallel": true, "self": 0.002526660000512493 } } } } } } }, "UnityEnvironment.step": { "total": 1511.3198244411299, "count": 64020, "is_parallel": true, "self": 36.68257018005738, "children": { "UnityEnvironment._generate_step_input": { "total": 24.401477550049094, "count": 64020, "is_parallel": true, "self": 24.401477550049094 }, "communicator.exchange": { "total": 1336.3907661129826, "count": 64020, "is_parallel": true, "self": 1336.3907661129826 }, "steps_from_proto": { "total": 113.84501059804074, "count": 64020, "is_parallel": true, "self": 22.824837182158035, "children": { "_process_rank_one_or_two_observation": { "total": 91.02017341588271, "count": 512160, "is_parallel": true, "self": 91.02017341588271 } } } } } } } } } } }, "trainer_advance": { "total": 680.4635653869141, "count": 64021, "self": 3.329480581980988, "children": { "process_trajectory": { "total": 117.87753685193275, "count": 64021, "self": 117.64868469293287, "children": { "RLTrainer._checkpoint": { "total": 0.22885215899987088, "count": 2, "self": 0.22885215899987088 } } }, "_update_policy": { "total": 559.2565479530003, "count": 452, "self": 364.3225147269627, "children": { "TorchPPOOptimizer.update": { "total": 194.93403322603763, "count": 22839, "self": 194.93403322603763 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.09682738699939364, "count": 1, "self": 0.001495374999649357, "children": { "RLTrainer._checkpoint": { "total": 0.09533201199974428, "count": 1, "self": 0.09533201199974428 } } } } } } }