{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1711047738790512, "min": 0.1711047738790512, "max": 1.3670471906661987, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5165.9951171875, "min": 5112.888671875, "max": 41470.7421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999956.0, "min": 29952.0, "max": 2999956.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999956.0, "min": 29952.0, "max": 2999956.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7012697458267212, "min": -0.10274841636419296, "max": 0.7841141819953918, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 206.87457275390625, "min": -24.76236915588379, "max": 238.0948486328125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.105246901512146, "min": -0.11711664497852325, "max": 0.6389044523239136, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -31.047836303710938, "min": -31.047836303710938, "max": 151.42034912109375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06874581631944131, "min": 0.06524686072652224, "max": 0.07395955533055322, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0311872447916197, "min": 0.4895255454821946, "max": 1.0622736555873418, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018043440165609926, "min": 0.0008893082782925362, "max": 0.018043440165609926, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2706516024841489, "min": 0.006225157948047753, "max": 0.2706516024841489, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.93255484226668e-07, "min": 4.93255484226668e-07, "max": 9.947112760929524e-05, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.398832263400021e-06, "min": 7.398832263400021e-06, "max": 0.0012676791876677998, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049310666666665, "min": 0.10049310666666665, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5073965999999999, "min": 1.3897045333333333, "max": 2.7675522, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.926135600000012e-05, "min": 5.926135600000012e-05, "max": 0.009946171977142858, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008889203400000019, "min": 0.0008889203400000019, "max": 0.12677846478000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005635115783661604, "min": 0.005635115783661604, "max": 0.30683016777038574, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08452674001455307, "min": 0.08159627765417099, "max": 2.1478111743927, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 263.05785123966945, "min": 226.96875, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31830.0, "min": 15984.0, "max": 33024.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7018330434013988, "min": -1.0000000521540642, "max": 1.7725275440478887, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.92179825156927, "min": -32.000001668930054, "max": 229.28659804165363, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7018330434013988, "min": -1.0000000521540642, "max": 1.7725275440478887, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.92179825156927, "min": -32.000001668930054, "max": 229.28659804165363, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031532756780988096, "min": 0.030531092308523206, "max": 15.359608789905906, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.81546357049956, "min": 3.668961188515823, "max": 245.7537406384945, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703718782", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703726628" }, "total": 7845.946613554001, "count": 1, "self": 0.53299095300099, "children": { "run_training.setup": { "total": 0.050693102999503026, "count": 1, "self": 0.050693102999503026 }, "TrainerController.start_learning": { "total": 7845.362929498, "count": 1, "self": 3.9631840981110145, "children": { "TrainerController._reset_env": { "total": 2.0664026499998727, "count": 1, "self": 2.0664026499998727 }, "TrainerController.advance": { "total": 7839.24765625789, "count": 194399, "self": 4.325357735843681, "children": { "env_step": { "total": 5033.434975645871, "count": 194399, "self": 4661.1675319249325, "children": { "SubprocessEnvManager._take_step": { "total": 369.9070303347962, "count": 194399, "self": 13.717549149207116, "children": { "TorchPolicy.evaluate": { "total": 356.1894811855891, "count": 187566, "self": 356.1894811855891 } } }, "workers": { "total": 2.3604133861426817, "count": 194399, "self": 0.0, "children": { "worker_root": { "total": 7831.540686625424, "count": 194399, "is_parallel": true, "self": 3510.9742184634724, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001694139999926847, "count": 1, "is_parallel": true, "self": 0.0005237280001892941, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011704119997375528, "count": 8, "is_parallel": true, "self": 0.0011704119997375528 } } }, "UnityEnvironment.step": { "total": 0.04993205000027956, "count": 1, "is_parallel": true, "self": 0.0005818609997731983, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004921270001432276, "count": 1, "is_parallel": true, "self": 0.0004921270001432276 }, "communicator.exchange": { "total": 0.04702113500025007, "count": 1, "is_parallel": true, "self": 0.04702113500025007 }, "steps_from_proto": { "total": 0.0018369270001130644, "count": 1, "is_parallel": true, "self": 0.00041359699753229506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014233300025807694, "count": 8, "is_parallel": true, "self": 0.0014233300025807694 } } } } } } }, "UnityEnvironment.step": { "total": 4320.566468161952, "count": 194398, "is_parallel": true, "self": 103.69883157763434, "children": { "UnityEnvironment._generate_step_input": { "total": 71.6286854790751, "count": 194398, "is_parallel": true, "self": 71.6286854790751 }, "communicator.exchange": { "total": 3853.8567942970194, "count": 194398, "is_parallel": true, "self": 3853.8567942970194 }, "steps_from_proto": { "total": 291.38215680822304, "count": 194398, "is_parallel": true, "self": 57.53613119344118, "children": { "_process_rank_one_or_two_observation": { "total": 233.84602561478187, "count": 1555184, "is_parallel": true, "self": 233.84602561478187 } } } } } } } } } } }, "trainer_advance": { "total": 2801.4873228761753, "count": 194399, "self": 7.931951546270284, "children": { "process_trajectory": { "total": 376.61744599693066, "count": 194399, "self": 376.07551620293, "children": { "RLTrainer._checkpoint": { "total": 0.54192979400068, "count": 6, "self": 0.54192979400068 } } }, "_update_policy": { "total": 2416.9379253329744, "count": 1391, "self": 1424.8100689359044, "children": { "TorchPPOOptimizer.update": { "total": 992.12785639707, "count": 114005, "self": 992.12785639707 } } } } } } }, "trainer_threads": { "total": 8.229999366449192e-07, "count": 1, "self": 8.229999366449192e-07 }, "TrainerController._save_models": { "total": 0.085685668998849, "count": 1, "self": 0.0022481369978777366, "children": { "RLTrainer._checkpoint": { "total": 0.08343753200097126, "count": 1, "self": 0.08343753200097126 } } } } } } }