{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41843748092651367, "min": 0.41843748092651367, "max": 1.3793894052505493, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12666.939453125, "min": 12641.6416015625, "max": 41845.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4093600809574127, "min": -0.10231993347406387, "max": 0.4513648748397827, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.93658447265625, "min": -24.659103393554688, "max": 123.22261047363281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017430000007152557, "min": -0.01870317943394184, "max": 0.43080365657806396, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.723529815673828, "min": -4.956342697143555, "max": 102.1004638671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06547939249563214, "min": 0.06467562513413264, "max": 0.07363205510257569, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.91671149493885, "min": 0.5154243857180298, "max": 1.0660530802201453, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015628467390131115, "min": 0.0001570021380403416, "max": 0.016801634147915783, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2187985434618356, "min": 0.002041027794524441, "max": 0.2515604453240808, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3180832749571425e-06, "min": 7.3180832749571425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001024531658494, "min": 0.0001024531658494, "max": 0.0035070593309802995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243932857142857, "min": 0.10243932857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341506, "min": 1.3886848, "max": 2.5690197000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002536889242857144, "min": 0.0002536889242857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003551644940000001, "min": 0.003551644940000001, "max": 0.11692506803, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009696995839476585, "min": 0.009696995839476585, "max": 0.44881197810173035, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1357579380273819, "min": 0.1357579380273819, "max": 3.14168381690979, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 439.36764705882354, "min": 390.14285714285717, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29877.0, "min": 15984.0, "max": 32991.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3840882166781847, "min": -1.0000000521540642, "max": 1.531916859088006, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.11799873411655, "min": -31.996001660823822, "max": 117.95759814977646, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3840882166781847, "min": -1.0000000521540642, "max": 1.531916859088006, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.11799873411655, "min": -31.996001660823822, "max": 117.95759814977646, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043902145883989496, "min": 0.03988872172141617, "max": 9.28834766894579, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9853459201112855, "min": 2.9853459201112855, "max": 148.61356270313263, "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": "1758206777", "python_version": "3.10.12 (main, Sep 18 2025, 14:42:15) [GCC 14.2.0]", "command_line_arguments": "/home/oxoghost/Documents/SynologyDrive/Python/DeepReinforcmentLearning/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "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": "1758207680" }, "total": 903.237450572, "count": 1, "self": 0.21849949500028742, "children": { "run_training.setup": { "total": 0.013732748000620632, "count": 1, "self": 0.013732748000620632 }, "TrainerController.start_learning": { "total": 903.005218328999, "count": 1, "self": 0.9637250945452251, "children": { "TrainerController._reset_env": { "total": 1.5384241490028217, "count": 1, "self": 1.5384241490028217 }, "TrainerController.advance": { "total": 900.4588757184465, "count": 63506, "self": 0.913288354397082, "children": { "env_step": { "total": 545.8305990077351, "count": 63506, "self": 467.52927184525834, "children": { "SubprocessEnvManager._take_step": { "total": 77.73637239923119, "count": 63506, "self": 2.785927560671553, "children": { "TorchPolicy.evaluate": { "total": 74.95044483855963, "count": 62557, "self": 74.95044483855963 } } }, "workers": { "total": 0.5649547632456233, "count": 63506, "self": 0.0, "children": { "worker_root": { "total": 901.7465879136653, "count": 63506, "is_parallel": true, "self": 494.5080576100372, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022714190017723013, "count": 1, "is_parallel": true, "self": 0.0007642689961357974, "children": { "_process_rank_one_or_two_observation": { "total": 0.001507150005636504, "count": 8, "is_parallel": true, "self": 0.001507150005636504 } } }, "UnityEnvironment.step": { "total": 0.021975046998704784, "count": 1, "is_parallel": true, "self": 0.00024002899590414017, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019551500008674338, "count": 1, "is_parallel": true, "self": 0.00019551500008674338 }, "communicator.exchange": { "total": 0.020834562001255108, "count": 1, "is_parallel": true, "self": 0.020834562001255108 }, "steps_from_proto": { "total": 0.000704941001458792, "count": 1, "is_parallel": true, "self": 0.00015936200725263916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005455789942061529, "count": 8, "is_parallel": true, "self": 0.0005455789942061529 } } } } } } }, "UnityEnvironment.step": { "total": 407.23853030362807, "count": 63505, "is_parallel": true, "self": 11.666603685789596, "children": { "UnityEnvironment._generate_step_input": { "total": 7.619309985588188, "count": 63505, "is_parallel": true, "self": 7.619309985588188 }, "communicator.exchange": { "total": 353.6968509032922, "count": 63505, "is_parallel": true, "self": 353.6968509032922 }, "steps_from_proto": { "total": 34.25576572895807, "count": 63505, "is_parallel": true, "self": 7.530080143289524, "children": { "_process_rank_one_or_two_observation": { "total": 26.725685585668543, "count": 508040, "is_parallel": true, "self": 26.725685585668543 } } } } } } } } } } }, "trainer_advance": { "total": 353.7149883563143, "count": 63506, "self": 1.5586463105937582, "children": { "process_trajectory": { "total": 66.74285309379411, "count": 63506, "self": 66.64260628879128, "children": { "RLTrainer._checkpoint": { "total": 0.10024680500282557, "count": 2, "self": 0.10024680500282557 } } }, "_update_policy": { "total": 285.4134889519264, "count": 449, "self": 180.91937746676922, "children": { "TorchPPOOptimizer.update": { "total": 104.49411148515719, "count": 22845, "self": 104.49411148515719 } } } } } } }, "trainer_threads": { "total": 7.24001438356936e-07, "count": 1, "self": 7.24001438356936e-07 }, "TrainerController._save_models": { "total": 0.044192643003043486, "count": 1, "self": 0.0006709390036121476, "children": { "RLTrainer._checkpoint": { "total": 0.04352170399943134, "count": 1, "self": 0.04352170399943134 } } } } } } }