{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.26472166180610657, "min": 0.26218485832214355, "max": 1.4483906030654907, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7937.41455078125, "min": 7937.41455078125, "max": 43938.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29903.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29903.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6507073640823364, "min": -0.07305789738893509, "max": 0.6815245151519775, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 188.05442810058594, "min": -17.606952667236328, "max": 196.279052734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007685417775064707, "min": -0.0217654500156641, "max": 0.28383108973503113, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.221085786819458, "min": -6.224918842315674, "max": 67.2679672241211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06821916964864137, "min": 0.06446253806427618, "max": 0.07321355226560773, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9550683750809792, "min": 0.5678890809959423, "max": 1.077926771288427, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017146701314015356, "min": 0.0018101252359135301, "max": 0.017146701314015356, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24005381839621498, "min": 0.019186233723606852, "max": 0.24005381839621498, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.533933203007143e-06, "min": 7.533933203007143e-06, "max": 0.000295289926570025, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010547506484210001, "min": 0.00010547506484210001, "max": 0.0036334930888356994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251127857142858, "min": 0.10251127857142858, "max": 0.19842997500000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351579, "min": 1.4351579, "max": 2.6622307000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026087672928571434, "min": 0.00026087672928571434, "max": 0.009843154502500001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036522742100000005, "min": 0.0036522742100000005, "max": 0.12113531357000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0109087023884058, "min": 0.0109087023884058, "max": 0.361594021320343, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1527218371629715, "min": 0.1527218371629715, "max": 2.892752170562744, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 277.03636363636366, "min": 275.36036036036035, "max": 982.4705882352941, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30474.0, "min": 16702.0, "max": 32919.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6865908979014916, "min": -0.9141636870124124, "max": 1.7066161921163936, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.52499876916409, "min": -30.167401671409607, "max": 189.4343973249197, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6865908979014916, "min": -0.9141636870124124, "max": 1.7066161921163936, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.52499876916409, "min": -30.167401671409607, "max": 189.4343973249197, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03143649511006184, "min": 0.03143649511006184, "max": 7.015895176459761, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.458014462106803, "min": 3.458014462106803, "max": 119.27021799981594, "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": "1766645136", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/Miniconda3/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": "1766647969" }, "total": 2833.1772355210014, "count": 1, "self": 0.3728790770037449, "children": { "run_training.setup": { "total": 0.04799070899935032, "count": 1, "self": 0.04799070899935032 }, "TrainerController.start_learning": { "total": 2832.7563657349983, "count": 1, "self": 2.6878751176554943, "children": { "TrainerController._reset_env": { "total": 3.392736485999194, "count": 1, "self": 3.392736485999194 }, "TrainerController.advance": { "total": 2826.5887846373425, "count": 64290, "self": 3.146422837529826, "children": { "env_step": { "total": 1776.3284749277445, "count": 64290, "self": 1498.2451657576094, "children": { "SubprocessEnvManager._take_step": { "total": 276.5500326644451, "count": 64290, "self": 9.602700344827099, "children": { "TorchPolicy.evaluate": { "total": 266.947332319618, "count": 62558, "self": 266.947332319618 } } }, "workers": { "total": 1.5332765056900826, "count": 64290, "self": 0.0, "children": { "worker_root": { "total": 2828.7491117876525, "count": 64290, "is_parallel": true, "self": 1493.713547606847, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015001700012362562, "count": 1, "is_parallel": true, "self": 0.0003299859981780173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011701840030582389, "count": 8, "is_parallel": true, "self": 0.0011701840030582389 } } }, "UnityEnvironment.step": { "total": 0.05536185199889587, "count": 1, "is_parallel": true, "self": 0.0005530149992409861, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003655679993244121, "count": 1, "is_parallel": true, "self": 0.0003655679993244121 }, "communicator.exchange": { "total": 0.05282722799893236, "count": 1, "is_parallel": true, "self": 0.05282722799893236 }, "steps_from_proto": { "total": 0.0016160410013981164, "count": 1, "is_parallel": true, "self": 0.0005256410004221834, "children": { "_process_rank_one_or_two_observation": { "total": 0.001090400000975933, "count": 8, "is_parallel": true, "self": 0.001090400000975933 } } } } } } }, "UnityEnvironment.step": { "total": 1335.0355641808055, "count": 64289, "is_parallel": true, "self": 34.23968950776725, "children": { "UnityEnvironment._generate_step_input": { "total": 21.507285192081326, "count": 64289, "is_parallel": true, "self": 21.507285192081326 }, "communicator.exchange": { "total": 1192.4805243461924, "count": 64289, "is_parallel": true, "self": 1192.4805243461924 }, "steps_from_proto": { "total": 86.80806513476455, "count": 64289, "is_parallel": true, "self": 21.715223353190595, "children": { "_process_rank_one_or_two_observation": { "total": 65.09284178157395, "count": 514312, "is_parallel": true, "self": 65.09284178157395 } } } } } } } } } } }, "trainer_advance": { "total": 1047.1138868720682, "count": 64290, "self": 5.569958914466042, "children": { "process_trajectory": { "total": 204.94459064164766, "count": 64290, "self": 204.72724696664773, "children": { "RLTrainer._checkpoint": { "total": 0.21734367499993823, "count": 2, "self": 0.21734367499993823 } } }, "_update_policy": { "total": 836.5993373159545, "count": 458, "self": 435.9535913070813, "children": { "TorchPPOOptimizer.update": { "total": 400.6457460088732, "count": 22794, "self": 400.6457460088732 } } } } } } }, "trainer_threads": { "total": 6.199989002197981e-07, "count": 1, "self": 6.199989002197981e-07 }, "TrainerController._save_models": { "total": 0.08696887400219566, "count": 1, "self": 0.0010264690026815515, "children": { "RLTrainer._checkpoint": { "total": 0.08594240499951411, "count": 1, "self": 0.08594240499951411 } } } } } } }