{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46428897976875305, "min": 0.4630119502544403, "max": 1.4515272378921509, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13936.09765625, "min": 13882.9501953125, "max": 44033.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5827290415763855, "min": -0.09187527745962143, "max": 0.6068825125694275, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.83322143554688, "min": -22.325693130493164, "max": 172.35462951660156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02060249075293541, "min": -0.03604922816157341, "max": 0.5022661685943604, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.6862874031066895, "min": -9.192553520202637, "max": 119.03707885742188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06793002985137893, "min": 0.06579567675602833, "max": 0.07442061584897332, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.951020417919305, "min": 0.5209443109428132, "max": 1.0631588473479496, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01580115235299759, "min": 0.0007982772323396237, "max": 0.015984586886285495, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22121613294196624, "min": 0.008781049555735861, "max": 0.2397688032942824, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.394754677971427e-06, "min": 7.394754677971427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010352656549159998, "min": 0.00010352656549159998, "max": 0.0033809651730117, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246488571428573, "min": 0.10246488571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345084000000003, "min": 1.3886848, "max": 2.5269883, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002562420828571428, "min": 0.0002562420828571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035873891599999997, "min": 0.0035873891599999997, "max": 0.11272613116999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010695296339690685, "min": 0.010462283156812191, "max": 0.5908074975013733, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14973415434360504, "min": 0.14647196233272552, "max": 4.135652542114258, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.69662921348316, "min": 308.0108695652174, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30055.0, "min": 15984.0, "max": 33437.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6173370539137486, "min": -1.0000000521540642, "max": 1.6783521554392318, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.94299779832363, "min": -28.513401605188847, "max": 160.71039752662182, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6173370539137486, "min": -1.0000000521540642, "max": 1.6783521554392318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.94299779832363, "min": -28.513401605188847, "max": 160.71039752662182, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03749218352254757, "min": 0.033715860175779315, "max": 12.377977542579174, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.336804333506734, "min": 3.101859136171697, "max": 198.04764068126678, "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": "1754705502", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --force", "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": "1754709232" }, "total": 3729.738556303999, "count": 1, "self": 0.6445959319989925, "children": { "run_training.setup": { "total": 0.038446603999545914, "count": 1, "self": 0.038446603999545914 }, "TrainerController.start_learning": { "total": 3729.0555137680003, "count": 1, "self": 2.28963634012689, "children": { "TrainerController._reset_env": { "total": 3.887441883000065, "count": 1, "self": 3.887441883000065 }, "TrainerController.advance": { "total": 3722.7952840078706, "count": 63884, "self": 2.3439564358723146, "children": { "env_step": { "total": 2588.390239493043, "count": 63884, "self": 2424.6425564839083, "children": { "SubprocessEnvManager._take_step": { "total": 162.19891957393338, "count": 63884, "self": 6.82594165316732, "children": { "TorchPolicy.evaluate": { "total": 155.37297792076606, "count": 62557, "self": 155.37297792076606 } } }, "workers": { "total": 1.548763435201181, "count": 63884, "self": 0.0, "children": { "worker_root": { "total": 3720.439933919284, "count": 63884, "is_parallel": true, "self": 1483.6614925151225, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008257895000497228, "count": 1, "is_parallel": true, "self": 0.0008630500033177668, "children": { "_process_rank_one_or_two_observation": { "total": 0.007394844997179462, "count": 8, "is_parallel": true, "self": 0.007394844997179462 } } }, "UnityEnvironment.step": { "total": 0.1092762340012996, "count": 1, "is_parallel": true, "self": 0.0007252190007420722, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005405150004662573, "count": 1, "is_parallel": true, "self": 0.0005405150004662573 }, "communicator.exchange": { "total": 0.10602921700046863, "count": 1, "is_parallel": true, "self": 0.10602921700046863 }, "steps_from_proto": { "total": 0.0019812829996226355, "count": 1, "is_parallel": true, "self": 0.0004126959993300261, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015685870002926094, "count": 8, "is_parallel": true, "self": 0.0015685870002926094 } } } } } } }, "UnityEnvironment.step": { "total": 2236.7784414041616, "count": 63883, "is_parallel": true, "self": 51.414079004200175, "children": { "UnityEnvironment._generate_step_input": { "total": 33.57934539992493, "count": 63883, "is_parallel": true, "self": 33.57934539992493 }, "communicator.exchange": { "total": 2006.5745213833197, "count": 63883, "is_parallel": true, "self": 2006.5745213833197 }, "steps_from_proto": { "total": 145.2104956167168, "count": 63883, "is_parallel": true, "self": 30.43937519780593, "children": { "_process_rank_one_or_two_observation": { "total": 114.77112041891087, "count": 511064, "is_parallel": true, "self": 114.77112041891087 } } } } } } } } } } }, "trainer_advance": { "total": 1132.0610880789554, "count": 63884, "self": 4.10727623512139, "children": { "process_trajectory": { "total": 168.6640824258193, "count": 63884, "self": 168.44927080281923, "children": { "RLTrainer._checkpoint": { "total": 0.21481162300005963, "count": 2, "self": 0.21481162300005963 } } }, "_update_policy": { "total": 959.2897294180148, "count": 450, "self": 392.01234423113965, "children": { "TorchPPOOptimizer.update": { "total": 567.2773851868751, "count": 22809, "self": 567.2773851868751 } } } } } } }, "trainer_threads": { "total": 1.4160013961372897e-06, "count": 1, "self": 1.4160013961372897e-06 }, "TrainerController._save_models": { "total": 0.0831501210013812, "count": 1, "self": 0.0018303590004506987, "children": { "RLTrainer._checkpoint": { "total": 0.0813197620009305, "count": 1, "self": 0.0813197620009305 } } } } } } }