{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5250925421714783, "min": 0.5250925421714783, "max": 1.4701387882232666, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15685.564453125, "min": 15685.564453125, "max": 44598.12890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29979.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29979.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27301257848739624, "min": -0.12793001532554626, "max": 0.31010231375694275, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 69.61820983886719, "min": -30.447341918945312, "max": 80.31649780273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010765371844172478, "min": -0.00022499257465824485, "max": 0.5418302416801453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7451698780059814, "min": -0.054673194885253906, "max": 128.95559692382812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06993935342133957, "min": 0.06566988492184983, "max": 0.07219877807905764, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0490903013200936, "min": 0.4920834284658803, "max": 1.0490903013200936, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01420253910555343, "min": 0.0004574477229942237, "max": 0.01486172111981432, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21303808658330145, "min": 0.004117029506948013, "max": 0.21303808658330145, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.501977499373333e-06, "min": 7.501977499373333e-06, "max": 0.00029523724444472857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001125296624906, "min": 0.0001125296624906, "max": 0.0031394468535178, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250062666666668, "min": 0.10250062666666668, "max": 0.19841241428571427, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375094000000002, "min": 1.3888869, "max": 2.4007173, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000259812604, "min": 0.000259812604, "max": 0.009841400187142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038971890600000007, "min": 0.0038971890600000007, "max": 0.10467357178, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011450548656284809, "min": 0.011450548656284809, "max": 0.3489531874656677, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.171758234500885, "min": 0.16367559134960175, "max": 2.4426722526550293, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 498.56140350877195, "min": 498.56140350877195, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28418.0, "min": 16650.0, "max": 32473.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.255754357890079, "min": -0.9999936006722911, "max": 1.255754357890079, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 71.5779983997345, "min": -31.999601677060127, "max": 71.5779983997345, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.255754357890079, "min": -0.9999936006722911, "max": 1.255754357890079, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 71.5779983997345, "min": -31.999601677060127, "max": 71.5779983997345, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05968442037211437, "min": 0.05968442037211437, "max": 6.843078768428634, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.402011961210519, "min": 3.402011961210519, "max": 116.33233906328678, "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": "1735420172", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735422305" }, "total": 2133.6128095259996, "count": 1, "self": 0.5271703579996938, "children": { "run_training.setup": { "total": 0.09472916000004261, "count": 1, "self": 0.09472916000004261 }, "TrainerController.start_learning": { "total": 2132.990910008, "count": 1, "self": 1.3555142679479104, "children": { "TrainerController._reset_env": { "total": 2.1510065620000205, "count": 1, "self": 2.1510065620000205 }, "TrainerController.advance": { "total": 2129.3930461920518, "count": 63373, "self": 1.4357720680495731, "children": { "env_step": { "total": 1438.7150318410395, "count": 63373, "self": 1287.1159522270405, "children": { "SubprocessEnvManager._take_step": { "total": 150.79945558089184, "count": 63373, "self": 4.636686686887515, "children": { "TorchPolicy.evaluate": { "total": 146.16276889400433, "count": 62562, "self": 146.16276889400433 } } }, "workers": { "total": 0.7996240331071931, "count": 63373, "self": 0.0, "children": { "worker_root": { "total": 2128.0341907050047, "count": 63373, "is_parallel": true, "self": 957.6517383869805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022348649999912595, "count": 1, "is_parallel": true, "self": 0.0007350920009230322, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014997729990682274, "count": 8, "is_parallel": true, "self": 0.0014997729990682274 } } }, "UnityEnvironment.step": { "total": 0.04873469899985139, "count": 1, "is_parallel": true, "self": 0.0006289409998316842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004775560000780388, "count": 1, "is_parallel": true, "self": 0.0004775560000780388 }, "communicator.exchange": { "total": 0.045872278999922855, "count": 1, "is_parallel": true, "self": 0.045872278999922855 }, "steps_from_proto": { "total": 0.0017559230000188109, "count": 1, "is_parallel": true, "self": 0.0003960759995607077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013598470004581031, "count": 8, "is_parallel": true, "self": 0.0013598470004581031 } } } } } } }, "UnityEnvironment.step": { "total": 1170.3824523180242, "count": 63372, "is_parallel": true, "self": 33.07074013713509, "children": { "UnityEnvironment._generate_step_input": { "total": 23.788007705957625, "count": 63372, "is_parallel": true, "self": 23.788007705957625 }, "communicator.exchange": { "total": 1013.8126401930031, "count": 63372, "is_parallel": true, "self": 1013.8126401930031 }, "steps_from_proto": { "total": 99.71106428192843, "count": 63372, "is_parallel": true, "self": 20.369639748121244, "children": { "_process_rank_one_or_two_observation": { "total": 79.34142453380719, "count": 506976, "is_parallel": true, "self": 79.34142453380719 } } } } } } } } } } }, "trainer_advance": { "total": 689.2422422829627, "count": 63373, "self": 2.531996254036585, "children": { "process_trajectory": { "total": 132.97342978992265, "count": 63373, "self": 132.77515346292284, "children": { "RLTrainer._checkpoint": { "total": 0.19827632699980313, "count": 2, "self": 0.19827632699980313 } } }, "_update_policy": { "total": 553.7368162390035, "count": 439, "self": 309.94946597504395, "children": { "TorchPPOOptimizer.update": { "total": 243.78735026395952, "count": 22815, "self": 243.78735026395952 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.09134197200000926, "count": 1, "self": 0.0016589810002187733, "children": { "RLTrainer._checkpoint": { "total": 0.08968299099979049, "count": 1, "self": 0.08968299099979049 } } } } } } }