{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2515838146209717, "min": 0.2515838146209717, "max": 0.9281170964241028, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 125775.8125, "min": 125775.8125, "max": 465008.9375, "count": 3 }, "Pyramids.Step.mean": { "value": 1499985.0, "min": 499954.0, "max": 1499985.0, "count": 3 }, "Pyramids.Step.sum": { "value": 1499985.0, "min": 499954.0, "max": 1499985.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6385899782180786, "min": -0.026637908071279526, "max": 0.6385899782180786, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 3011.59033203125, "min": -107.5372314453125, "max": 3011.59033203125, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011957109905779362, "min": 0.011957109905779362, "max": 0.10038905590772629, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 56.389732360839844, "min": 56.389732360839844, "max": 405.2706298828125, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0689566359084375, "min": 0.0689566359084375, "max": 0.06965800307636422, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 16.273766074391247, "min": 15.04612866449467, "max": 16.369983259605025, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0154182042217595, "min": 0.0036109710444816234, "max": 0.0154182042217595, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 3.6386961963352418, "min": 0.7799697456080307, "max": 3.6386961963352418, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.002008756395339e-05, "min": 5.002008756395339e-05, "max": 0.0002471372555838836, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.011804740665092999, "min": 0.011804740665092999, "max": 0.05338164720611886, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11667333474576272, "min": 0.11667333474576272, "max": 0.18237907932098768, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 27.534907, "min": 27.534907, "max": 39.39388113333334, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.001675666141101695, "min": 0.001675666141101695, "max": 0.008239670024166666, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.3954572093, "min": 0.3954572093, "max": 1.7797687252199998, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009781146422028542, "min": 0.009781146422028542, "max": 0.06692411750555038, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.3083505630493164, "min": 2.3083505630493164, "max": 14.455609321594238, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 298.86746987951807, "min": 298.86746987951807, "max": 910.3814814814815, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 496120.0, "min": 491606.0, "max": 504712.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6624684599893433, "min": -0.4925648632148902, "max": 1.6624684599893433, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 2758.0351751223207, "min": -265.9850261360407, "max": 2758.0351751223207, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6624684599893433, "min": -0.4925648632148902, "max": 1.6624684599893433, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 2758.0351751223207, "min": -265.9850261360407, "max": 2758.0351751223207, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030314551268771354, "min": 0.030314551268771354, "max": 0.8964704334823181, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 50.29184055489168, "min": 50.29184055489168, "max": 484.0940340804518, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1747493365", "python_version": "3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0]", "command_line_arguments": "/home/emanuele/miniconda3/envs/mlagents/bin/mlagents-learn /home/emanuele/Projects/ml-agents/config/ppo/PyramidsRND.yaml --env=./trained-env/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747494812" }, "total": 1446.9525540070026, "count": 1, "self": 0.26821221499994863, "children": { "run_training.setup": { "total": 0.029213972000434296, "count": 1, "self": 0.029213972000434296 }, "TrainerController.start_learning": { "total": 1446.6551278200022, "count": 1, "self": 1.3333391938795103, "children": { "TrainerController._reset_env": { "total": 1.5117400659983105, "count": 1, "self": 1.5117400659983105 }, "TrainerController.advance": { "total": 1443.75999684813, "count": 96226, "self": 1.2650744448110345, "children": { "env_step": { "total": 844.8972788394458, "count": 96226, "self": 699.6834533022629, "children": { "SubprocessEnvManager._take_step": { "total": 144.34960608169058, "count": 96226, "self": 3.6151293190414435, "children": { "TorchPolicy.evaluate": { "total": 140.73447676264914, "count": 93811, "self": 140.73447676264914 } } }, "workers": { "total": 0.8642194554922753, "count": 96226, "self": 0.0, "children": { "worker_root": { "total": 1444.9820853533129, "count": 96226, "is_parallel": true, "self": 828.1885443474057, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009029969987750519, "count": 1, "is_parallel": true, "self": 0.0002597259954200126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006432710033550393, "count": 8, "is_parallel": true, "self": 0.0006432710033550393 } } }, "UnityEnvironment.step": { "total": 0.018335690001549665, "count": 1, "is_parallel": true, "self": 0.00019816100029856898, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017351900169160217, "count": 1, "is_parallel": true, "self": 0.00017351900169160217 }, "communicator.exchange": { "total": 0.01738346099955379, "count": 1, "is_parallel": true, "self": 0.01738346099955379 }, "steps_from_proto": { "total": 0.0005805490000057034, "count": 1, "is_parallel": true, "self": 0.00014545498925144784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004350940107542556, "count": 8, "is_parallel": true, "self": 0.0004350940107542556 } } } } } } }, "UnityEnvironment.step": { "total": 616.7935410059072, "count": 96225, "is_parallel": true, "self": 17.021691362344427, "children": { "UnityEnvironment._generate_step_input": { "total": 12.463479850128351, "count": 96225, "is_parallel": true, "self": 12.463479850128351 }, "communicator.exchange": { "total": 535.8643497009289, "count": 96225, "is_parallel": true, "self": 535.8643497009289 }, "steps_from_proto": { "total": 51.444020092505525, "count": 96225, "is_parallel": true, "self": 12.272127446285594, "children": { "_process_rank_one_or_two_observation": { "total": 39.17189264621993, "count": 769800, "is_parallel": true, "self": 39.17189264621993 } } } } } } } } } } }, "trainer_advance": { "total": 597.5976435638731, "count": 96226, "self": 2.406830608018936, "children": { "process_trajectory": { "total": 112.46834012189356, "count": 96226, "self": 112.2985004908951, "children": { "RLTrainer._checkpoint": { "total": 0.16983963099846733, "count": 3, "self": 0.16983963099846733 } } }, "_update_policy": { "total": 482.72247283396064, "count": 689, "self": 258.6164132410304, "children": { "TorchPPOOptimizer.update": { "total": 224.10605959293025, "count": 34173, "self": 224.10605959293025 } } } } } } }, "trainer_threads": { "total": 5.919973773416132e-07, "count": 1, "self": 5.919973773416132e-07 }, "TrainerController._save_models": { "total": 0.050051119997078786, "count": 1, "self": 0.0008243349984695669, "children": { "RLTrainer._checkpoint": { "total": 0.04922678499860922, "count": 1, "self": 0.04922678499860922 } } } } } } }