{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3662203252315521, "min": 0.35252490639686584, "max": 1.4821102619171143, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10963.171875, "min": 10575.7470703125, "max": 44961.296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.581268310546875, "min": -0.06992906332015991, "max": 0.6206590533256531, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.84878540039062, "min": -16.922832489013672, "max": 170.68124389648438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.029434269294142723, "min": -0.029434269294142723, "max": 0.6096308827400208, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.0944242477417, "min": -8.0944242477417, "max": 144.48251342773438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07414545548783194, "min": 0.06402237467312565, "max": 0.07414545548783194, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0380363768296472, "min": 0.49986444515291195, "max": 1.0927377134817193, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013442317180479654, "min": 0.0024263131573948127, "max": 0.016615065985423002, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18819244052671516, "min": 0.029165011096455917, "max": 0.23855689145007183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.390983250657146e-06, "min": 7.390983250657146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010347376550920005, "min": 0.00010347376550920005, "max": 0.0037578970473676997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246362857142861, "min": 0.10246362857142861, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344908000000005, "min": 1.3886848, "max": 2.6526323000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002561164942857143, "min": 0.0002561164942857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003585630920000001, "min": 0.003585630920000001, "max": 0.12527796677, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011244603432714939, "min": 0.010602102614939213, "max": 0.6331111192703247, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1574244499206543, "min": 0.14842943847179413, "max": 4.4317779541015625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.125, "min": 309.421568627451, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28410.0, "min": 15984.0, "max": 33018.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4948299762792885, "min": -1.0000000521540642, "max": 1.6271746943051788, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.58639810234308, "min": -28.753001734614372, "max": 164.43679846078157, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4948299762792885, "min": -1.0000000521540642, "max": 1.6271746943051788, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.58639810234308, "min": -28.753001734614372, "max": 164.43679846078157, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0406228395191647, "min": 0.0352157667700393, "max": 13.469349486753345, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.249827161533176, "min": 3.232574724650476, "max": 215.5095917880535, "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": "1692617401", "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": "1692619753" }, "total": 2352.457404783, "count": 1, "self": 0.47630618900075206, "children": { "run_training.setup": { "total": 0.06715090199986662, "count": 1, "self": 0.06715090199986662 }, "TrainerController.start_learning": { "total": 2351.9139476919995, "count": 1, "self": 1.5221912529486872, "children": { "TrainerController._reset_env": { "total": 4.95491548300015, "count": 1, "self": 4.95491548300015 }, "TrainerController.advance": { "total": 2345.3390180540514, "count": 64092, "self": 1.4225067220868368, "children": { "env_step": { "total": 1693.9282755859235, "count": 64092, "self": 1582.8220088259372, "children": { "SubprocessEnvManager._take_step": { "total": 110.24129824408374, "count": 64092, "self": 4.769488856039516, "children": { "TorchPolicy.evaluate": { "total": 105.47180938804422, "count": 62559, "self": 105.47180938804422 } } }, "workers": { "total": 0.8649685159025466, "count": 64092, "self": 0.0, "children": { "worker_root": { "total": 2346.6364319910535, "count": 64092, "is_parallel": true, "self": 881.423678519021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026366130000496923, "count": 1, "is_parallel": true, "self": 0.0007060830002956209, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019305299997540715, "count": 8, "is_parallel": true, "self": 0.0019305299997540715 } } }, "UnityEnvironment.step": { "total": 0.050637370999993436, "count": 1, "is_parallel": true, "self": 0.0005476369997268193, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005072009998912108, "count": 1, "is_parallel": true, "self": 0.0005072009998912108 }, "communicator.exchange": { "total": 0.04774446000010357, "count": 1, "is_parallel": true, "self": 0.04774446000010357 }, "steps_from_proto": { "total": 0.0018380730002718337, "count": 1, "is_parallel": true, "self": 0.00034648499968170654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014915880005901272, "count": 8, "is_parallel": true, "self": 0.0014915880005901272 } } } } } } }, "UnityEnvironment.step": { "total": 1465.2127534720325, "count": 64091, "is_parallel": true, "self": 34.342037267894284, "children": { "UnityEnvironment._generate_step_input": { "total": 22.65537818404846, "count": 64091, "is_parallel": true, "self": 22.65537818404846 }, "communicator.exchange": { "total": 1301.3639940570392, "count": 64091, "is_parallel": true, "self": 1301.3639940570392 }, "steps_from_proto": { "total": 106.85134396305057, "count": 64091, "is_parallel": true, "self": 21.160973099130388, "children": { "_process_rank_one_or_two_observation": { "total": 85.69037086392018, "count": 512728, "is_parallel": true, "self": 85.69037086392018 } } } } } } } } } } }, "trainer_advance": { "total": 649.988235746041, "count": 64092, "self": 2.7474069830245753, "children": { "process_trajectory": { "total": 111.35380878300975, "count": 64092, "self": 111.15067750301068, "children": { "RLTrainer._checkpoint": { "total": 0.2031312799990701, "count": 2, "self": 0.2031312799990701 } } }, "_update_policy": { "total": 535.8870199800067, "count": 457, "self": 348.2779830689865, "children": { "TorchPPOOptimizer.update": { "total": 187.6090369110202, "count": 22788, "self": 187.6090369110202 } } } } } } }, "trainer_threads": { "total": 8.139995770761743e-07, "count": 1, "self": 8.139995770761743e-07 }, "TrainerController._save_models": { "total": 0.09782208799970249, "count": 1, "self": 0.0014795580000281916, "children": { "RLTrainer._checkpoint": { "total": 0.0963425299996743, "count": 1, "self": 0.0963425299996743 } } } } } } }