{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -3.576278402306343e-07, "max": 2.853149175643921, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": -0.0034185645636171103, "min": -0.0037214753683656454, "max": 29250.486328125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5494749546051025, "min": 0.23019982874393463, "max": 1.8132851123809814, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 107.14762115478516, "min": 44.65876770019531, "max": 371.72344970703125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 6.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 272.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": 0.0, "max": 6.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": 0.0, "max": 272.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04698769247761091, "min": 0.045914910217377876, "max": 0.17927464174830487, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.09397538495522181, "min": 0.09182982043475575, "max": 0.5378239252449146, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.00022483321179107388, "min": 0.00014167892710318877, "max": 0.21930968309227633, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.00044966642358214775, "min": 0.00028335785420637754, "max": 0.43861936618455266, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432009785600003e-05, "min": 6.432009785600003e-05, "max": 0.002902320003256, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00012864019571200006, "min": 0.00012864019571200006, "max": 0.007419960052668, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102144, "min": 0.102144, "max": 0.196744, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.204288, "min": 0.204288, "max": 0.547332, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001169856000000001, "min": 0.0001169856000000001, "max": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002339712000000002, "min": 0.0002339712000000002, "max": 0.012371866799999999, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713945534", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713946610" }, "total": 1075.6014756499999, "count": 1, "self": 0.43132703399987804, "children": { "run_training.setup": { "total": 0.06342404599996598, "count": 1, "self": 0.06342404599996598 }, "TrainerController.start_learning": { "total": 1075.10672457, "count": 1, "self": 0.5901515229929828, "children": { "TrainerController._reset_env": { "total": 2.6713747379999973, "count": 1, "self": 2.6713747379999973 }, "TrainerController.advance": { "total": 1071.3782294240073, "count": 18203, "self": 0.28343075201655665, "children": { "env_step": { "total": 1071.0947986719907, "count": 18203, "self": 916.2595843850149, "children": { "SubprocessEnvManager._take_step": { "total": 154.5302365419803, "count": 18203, "self": 1.5045670279858427, "children": { "TorchPolicy.evaluate": { "total": 153.02566951399444, "count": 18203, "self": 153.02566951399444 } } }, "workers": { "total": 0.30497774499548314, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 1073.5785019270015, "count": 18203, "is_parallel": true, "self": 863.7435115420095, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004702709000014238, "count": 1, "is_parallel": true, "self": 0.003213532000017949, "children": { "_process_rank_one_or_two_observation": { "total": 0.001489176999996289, "count": 10, "is_parallel": true, "self": 0.001489176999996289 } } }, "UnityEnvironment.step": { "total": 0.04085419099999399, "count": 1, "is_parallel": true, "self": 0.0006584569999290579, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003934070000468637, "count": 1, "is_parallel": true, "self": 0.0003934070000468637 }, "communicator.exchange": { "total": 0.037712424999995164, "count": 1, "is_parallel": true, "self": 0.037712424999995164 }, "steps_from_proto": { "total": 0.002089902000022903, "count": 1, "is_parallel": true, "self": 0.0004004000001032182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016895019999196847, "count": 10, "is_parallel": true, "self": 0.0016895019999196847 } } } } } } }, "UnityEnvironment.step": { "total": 209.834990384992, "count": 18202, "is_parallel": true, "self": 10.63633701399283, "children": { "UnityEnvironment._generate_step_input": { "total": 5.761099173005675, "count": 18202, "is_parallel": true, "self": 5.761099173005675 }, "communicator.exchange": { "total": 157.45708275600202, "count": 18202, "is_parallel": true, "self": 157.45708275600202 }, "steps_from_proto": { "total": 35.98047144199148, "count": 18202, "is_parallel": true, "self": 6.818430501001103, "children": { "_process_rank_one_or_two_observation": { "total": 29.16204094099038, "count": 182020, "is_parallel": true, "self": 29.16204094099038 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019592099988585687, "count": 1, "self": 0.00019592099988585687, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1064.1910759700527, "count": 826578, "is_parallel": true, "self": 18.191081803151974, "children": { "process_trajectory": { "total": 292.7390154439006, "count": 826578, "is_parallel": true, "self": 289.66322821290066, "children": { "RLTrainer._checkpoint": { "total": 3.0757872309999357, "count": 4, "is_parallel": true, "self": 3.0757872309999357 } } }, "_update_policy": { "total": 753.2609787230001, "count": 45, "is_parallel": true, "self": 415.6952496390069, "children": { "TorchPPOOptimizer.update": { "total": 337.56572908399323, "count": 22920, "is_parallel": true, "self": 337.56572908399323 } } } } } } } } }, "TrainerController._save_models": { "total": 0.4667729640000289, "count": 1, "self": 0.017649950000077297, "children": { "RLTrainer._checkpoint": { "total": 0.4491230139999516, "count": 1, "self": 0.4491230139999516 } } } } } } }