{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3526631295681, "min": 0.3513202369213104, "max": 1.4167109727859497, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10732.244140625, "min": 10588.779296875, "max": 42977.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43950238823890686, "min": -0.10878261923789978, "max": 0.5653785467147827, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.34713745117188, "min": -26.216611862182617, "max": 156.60986328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013930845074355602, "min": -0.047410301864147186, "max": 0.4652758836746216, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.7195355892181396, "min": -12.80078125, "max": 112.13148498535156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06899824628739486, "min": 0.06479242677492689, "max": 0.0744466115138274, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.965975448023528, "min": 0.49691166631755657, "max": 1.060204450865664, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01321612164714939, "min": 0.0006442169138658835, "max": 0.016102025216761313, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18502570306009147, "min": 0.00901903679412237, "max": 0.22542835303465836, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.287290428078572e-06, "min": 7.287290428078572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001020220659931, "min": 0.0001020220659931, "max": 0.0035077262307579996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242906428571429, "min": 0.10242906428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340069, "min": 1.3886848, "max": 2.5692420000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002526635221428572, "min": 0.0002526635221428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003537289310000001, "min": 0.003537289310000001, "max": 0.1169472758, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015263828448951244, "min": 0.015263828448951244, "max": 0.7572814226150513, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21369360387325287, "min": 0.21369360387325287, "max": 5.300970077514648, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 422.4246575342466, "min": 333.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30837.0, "min": 15984.0, "max": 32887.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4405479216820574, "min": -1.0000000521540642, "max": 1.6251788030652439, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.15999828279018, "min": -30.13940168917179, "max": 138.14019826054573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4405479216820574, "min": -1.0000000521540642, "max": 1.6251788030652439, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.15999828279018, "min": -30.13940168917179, "max": 138.14019826054573, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06638082858940111, "min": 0.05483552775694989, "max": 15.315701624378562, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.845800487026281, "min": 4.551348803826841, "max": 245.051225990057, "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": "1791708935", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mla/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --torch-device=cpu", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1791711270" }, "total": 2334.7493050449993, "count": 1, "self": 1.0409441819992935, "children": { "run_training.setup": { "total": 0.020575319999807107, "count": 1, "self": 0.020575319999807107 }, "TrainerController.start_learning": { "total": 2333.6877855430002, "count": 1, "self": 1.3382657588663278, "children": { "TrainerController._reset_env": { "total": 1.7287996939994628, "count": 1, "self": 1.7287996939994628 }, "TrainerController.advance": { "total": 2330.537647957134, "count": 63819, "self": 1.373389015590874, "children": { "env_step": { "total": 1628.4385265032379, "count": 63819, "self": 1525.7696434945037, "children": { "SubprocessEnvManager._take_step": { "total": 101.83112923272893, "count": 63819, "self": 4.778971533579352, "children": { "TorchPolicy.evaluate": { "total": 97.05215769914957, "count": 62565, "self": 97.05215769914957 } } }, "workers": { "total": 0.8377537760052292, "count": 63819, "self": 0.0, "children": { "worker_root": { "total": 2327.905690405819, "count": 63819, "is_parallel": true, "self": 924.4724831638641, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017823919997681514, "count": 1, "is_parallel": true, "self": 0.0005801060005978798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012022859991702717, "count": 8, "is_parallel": true, "self": 0.0012022859991702717 } } }, "UnityEnvironment.step": { "total": 0.05253932799951144, "count": 1, "is_parallel": true, "self": 0.0005856670004504849, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005126699998072581, "count": 1, "is_parallel": true, "self": 0.0005126699998072581 }, "communicator.exchange": { "total": 0.049550925999938045, "count": 1, "is_parallel": true, "self": 0.049550925999938045 }, "steps_from_proto": { "total": 0.0018900649993156549, "count": 1, "is_parallel": true, "self": 0.000401061998672958, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014890030006426969, "count": 8, "is_parallel": true, "self": 0.0014890030006426969 } } } } } } }, "UnityEnvironment.step": { "total": 1403.4332072419547, "count": 63818, "is_parallel": true, "self": 33.23449277524833, "children": { "UnityEnvironment._generate_step_input": { "total": 21.632457034955223, "count": 63818, "is_parallel": true, "self": 21.632457034955223 }, "communicator.exchange": { "total": 1238.164477230841, "count": 63818, "is_parallel": true, "self": 1238.164477230841 }, "steps_from_proto": { "total": 110.40178020091025, "count": 63818, "is_parallel": true, "self": 23.43339752805059, "children": { "_process_rank_one_or_two_observation": { "total": 86.96838267285966, "count": 510544, "is_parallel": true, "self": 86.96838267285966 } } } } } } } } } } }, "trainer_advance": { "total": 700.7257324383054, "count": 63819, "self": 2.5578068872146105, "children": { "process_trajectory": { "total": 111.70998967809282, "count": 63819, "self": 111.51228127309332, "children": { "RLTrainer._checkpoint": { "total": 0.19770840499950282, "count": 2, "self": 0.19770840499950282 } } }, "_update_policy": { "total": 586.457935872998, "count": 451, "self": 261.1894061569383, "children": { "TorchPPOOptimizer.update": { "total": 325.2685297160597, "count": 22836, "self": 325.2685297160597 } } } } } } }, "trainer_threads": { "total": 1.4769993867957965e-06, "count": 1, "self": 1.4769993867957965e-06 }, "TrainerController._save_models": { "total": 0.08307065600092756, "count": 1, "self": 0.0014787630007049302, "children": { "RLTrainer._checkpoint": { "total": 0.08159189300022263, "count": 1, "self": 0.08159189300022263 } } } } } } }