{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3672098219394684, "min": 0.3672098219394684, "max": 1.4855825901031494, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11063.2978515625, "min": 11063.2978515625, "max": 45066.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29942.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29942.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.674055814743042, "min": -0.2825426757335663, "max": 0.6962081789970398, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 194.12808227539062, "min": -66.96261596679688, "max": 199.81175231933594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0028121694922447205, "min": -0.027128567919135094, "max": 0.4172181785106659, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8099048137664795, "min": -7.7858991622924805, "max": 98.88070678710938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06958583950688567, "min": 0.06337483075566568, "max": 0.07399136097535956, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9742017530963994, "min": 0.5105156164304233, "max": 1.081377664435422, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014628668583064412, "min": 0.0008890320008018288, "max": 0.016911242134353546, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20480136016290176, "min": 0.010668384009621945, "max": 0.23675738988094966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.729511709242858e-06, "min": 7.729511709242858e-06, "max": 0.0002952333444460286, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001082131639294, "min": 0.0001082131639294, "max": 0.0036333781888739994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257647142857143, "min": 0.10257647142857143, "max": 0.19841111428571429, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360706, "min": 1.3888778, "max": 2.6111259999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002673894957142858, "min": 0.0002673894957142858, "max": 0.009841270317142856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003743452940000001, "min": 0.003743452940000001, "max": 0.1211314874, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015071366913616657, "min": 0.015071366913616657, "max": 0.6225557923316956, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21099913120269775, "min": 0.21099913120269775, "max": 4.357890605926514, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.375, "min": 272.375, "max": 998.125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30506.0, "min": 16613.0, "max": 33227.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7097606999533517, "min": -0.9365063032601029, "max": 1.7256826768414333, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.4931983947754, "min": -29.968201704323292, "max": 191.4931983947754, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7097606999533517, "min": -0.9365063032601029, "max": 1.7256826768414333, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.4931983947754, "min": -29.968201704323292, "max": 191.4931983947754, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042177012308716906, "min": 0.042177012308716906, "max": 11.632182612138635, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.723825378576294, "min": 4.723825378576294, "max": 197.7471044063568, "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": "1788413348", "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", "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": "1788415782" }, "total": 2434.1207531959994, "count": 1, "self": 0.47934787299936943, "children": { "run_training.setup": { "total": 0.024517126999853645, "count": 1, "self": 0.024517126999853645 }, "TrainerController.start_learning": { "total": 2433.616888196, "count": 1, "self": 1.457469365875113, "children": { "TrainerController._reset_env": { "total": 2.1985134040000958, "count": 1, "self": 2.1985134040000958 }, "TrainerController.advance": { "total": 2429.870155017125, "count": 64219, "self": 1.4123624210533308, "children": { "env_step": { "total": 1788.688890753052, "count": 64219, "self": 1634.7637004461658, "children": { "SubprocessEnvManager._take_step": { "total": 153.10362278591901, "count": 64219, "self": 4.8594479419857635, "children": { "TorchPolicy.evaluate": { "total": 148.24417484393325, "count": 62561, "self": 148.24417484393325 } } }, "workers": { "total": 0.8215675209671645, "count": 64219, "self": 0.0, "children": { "worker_root": { "total": 2427.54102250091, "count": 64219, "is_parallel": true, "self": 911.8508559099291, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018608880000101635, "count": 1, "is_parallel": true, "self": 0.0006088409995754773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012520470004346862, "count": 8, "is_parallel": true, "self": 0.0012520470004346862 } } }, "UnityEnvironment.step": { "total": 0.10919445200033806, "count": 1, "is_parallel": true, "self": 0.000576521000766661, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005369499999687832, "count": 1, "is_parallel": true, "self": 0.0005369499999687832 }, "communicator.exchange": { "total": 0.10213089999979275, "count": 1, "is_parallel": true, "self": 0.10213089999979275 }, "steps_from_proto": { "total": 0.00595008099980987, "count": 1, "is_parallel": true, "self": 0.0004724499999610998, "children": { "_process_rank_one_or_two_observation": { "total": 0.0054776309998487704, "count": 8, "is_parallel": true, "self": 0.0054776309998487704 } } } } } } }, "UnityEnvironment.step": { "total": 1515.6901665909809, "count": 64218, "is_parallel": true, "self": 33.98894883990806, "children": { "UnityEnvironment._generate_step_input": { "total": 23.626191271999687, "count": 64218, "is_parallel": true, "self": 23.626191271999687 }, "communicator.exchange": { "total": 1346.9420184709752, "count": 64218, "is_parallel": true, "self": 1346.9420184709752 }, "steps_from_proto": { "total": 111.13300800809793, "count": 64218, "is_parallel": true, "self": 23.31556741504528, "children": { "_process_rank_one_or_two_observation": { "total": 87.81744059305265, "count": 513744, "is_parallel": true, "self": 87.81744059305265 } } } } } } } } } } }, "trainer_advance": { "total": 639.7689018430196, "count": 64219, "self": 2.7047553168331433, "children": { "process_trajectory": { "total": 115.14689205018385, "count": 64219, "self": 114.95962112018424, "children": { "RLTrainer._checkpoint": { "total": 0.18727092999961314, "count": 2, "self": 0.18727092999961314 } } }, "_update_policy": { "total": 521.9172544760027, "count": 458, "self": 279.64537723502735, "children": { "TorchPPOOptimizer.update": { "total": 242.2718772409753, "count": 22788, "self": 242.2718772409753 } } } } } } }, "trainer_threads": { "total": 1.088000317395199e-06, "count": 1, "self": 1.088000317395199e-06 }, "TrainerController._save_models": { "total": 0.0907493209997483, "count": 1, "self": 0.0014281979993029381, "children": { "RLTrainer._checkpoint": { "total": 0.08932112300044537, "count": 1, "self": 0.08932112300044537 } } } } } } }