{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9185134768486023, "min": 0.9120550751686096, "max": 2.87385630607605, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8780.0703125, "min": 8780.0703125, "max": 29431.162109375, "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": 12.94749641418457, "min": 0.3477676510810852, "max": 12.94749641418457, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.76171875, "min": 67.46692657470703, "max": 2616.76904296875, "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.Losses.PolicyLoss.mean": { "value": 0.06378449137307196, "min": 0.06214164333456816, "max": 0.07467440665812533, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25513796549228784, "min": 0.25513796549228784, "max": 0.3625743786220019, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2035373322227422, "min": 0.11063141474276597, "max": 0.2749004583732754, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8141493288909688, "min": 0.4425256589710639, "max": 1.3745022918663772, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.136363636363637, "min": 3.272727272727273, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 144.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.272727272727273, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 144.0, "max": 1408.0, "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": "1726857046", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726857665" }, "total": 618.9686172340001, "count": 1, "self": 0.5443675240002221, "children": { "run_training.setup": { "total": 0.10438712600000599, "count": 1, "self": 0.10438712600000599 }, "TrainerController.start_learning": { "total": 618.3198625839999, "count": 1, "self": 0.8609638699729203, "children": { "TrainerController._reset_env": { "total": 2.6275700909999387, "count": 1, "self": 2.6275700909999387 }, "TrainerController.advance": { "total": 614.7426361310272, "count": 18203, "self": 0.44064555202066913, "children": { "env_step": { "total": 614.3019905790065, "count": 18203, "self": 467.5184239439992, "children": { "SubprocessEnvManager._take_step": { "total": 146.36146111101368, "count": 18203, "self": 2.543026992010141, "children": { "TorchPolicy.evaluate": { "total": 143.81843411900354, "count": 18203, "self": 143.81843411900354 } } }, "workers": { "total": 0.4221055239936504, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 616.2903925199988, "count": 18203, "is_parallel": true, "self": 295.4879247519907, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034145690000286777, "count": 1, "is_parallel": true, "self": 0.0010206819999893924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023938870000392853, "count": 10, "is_parallel": true, "self": 0.0023938870000392853 } } }, "UnityEnvironment.step": { "total": 0.1063581159999103, "count": 1, "is_parallel": true, "self": 0.000897049000059269, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043233700000655517, "count": 1, "is_parallel": true, "self": 0.00043233700000655517 }, "communicator.exchange": { "total": 0.10203477199991084, "count": 1, "is_parallel": true, "self": 0.10203477199991084 }, "steps_from_proto": { "total": 0.0029939579999336274, "count": 1, "is_parallel": true, "self": 0.00045190399987404817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025420540000595793, "count": 10, "is_parallel": true, "self": 0.0025420540000595793 } } } } } } }, "UnityEnvironment.step": { "total": 320.8024677680081, "count": 18202, "is_parallel": true, "self": 15.245553983022432, "children": { "UnityEnvironment._generate_step_input": { "total": 7.756666070988558, "count": 18202, "is_parallel": true, "self": 7.756666070988558 }, "communicator.exchange": { "total": 252.76196742699403, "count": 18202, "is_parallel": true, "self": 252.76196742699403 }, "steps_from_proto": { "total": 45.03828028700309, "count": 18202, "is_parallel": true, "self": 8.97154330206979, "children": { "_process_rank_one_or_two_observation": { "total": 36.0667369849333, "count": 182020, "is_parallel": true, "self": 36.0667369849333 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016515399988747959, "count": 1, "self": 0.00016515399988747959, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 607.154527440058, "count": 787893, "is_parallel": true, "self": 19.393605928037914, "children": { "process_trajectory": { "total": 325.9650455980217, "count": 787893, "is_parallel": true, "self": 325.2756923630217, "children": { "RLTrainer._checkpoint": { "total": 0.6893532349999987, "count": 4, "is_parallel": true, "self": 0.6893532349999987 } } }, "_update_policy": { "total": 261.79587591399843, "count": 90, "is_parallel": true, "self": 74.13187471099639, "children": { "TorchPPOOptimizer.update": { "total": 187.66400120300204, "count": 4587, "is_parallel": true, "self": 187.66400120300204 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08852733799994894, "count": 1, "self": 0.0012472859998524655, "children": { "RLTrainer._checkpoint": { "total": 0.08728005200009648, "count": 1, "self": 0.08728005200009648 } } } } } } }