{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9413912296295166, "min": 0.9413912296295166, "max": 2.8696532249450684, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9050.53515625, "min": 9050.53515625, "max": 29482.818359375, "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": 12.678226470947266, "min": 0.3221913278102875, "max": 12.678226470947266, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2472.254150390625, "min": 62.50511932373047, "max": 2553.999755859375, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.009558119811117649, "min": 0.008217559196054935, "max": 0.015569817274808884, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 1.8638333082199097, "min": 1.5942065715789795, "max": 3.0251717567443848, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06550769321220999, "min": 0.05627972948316122, "max": 0.07766587582001622, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26203077284883997, "min": 0.22511891793264488, "max": 0.3643824107065324, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.09813455576259716, "min": 0.0542354859490468, "max": 0.15251043497347364, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.39253822305038866, "min": 0.2169419437961872, "max": 0.692256245542975, "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.Losses.CuriosityForwardLoss.mean": { "value": 0.03834085802858075, "min": 0.0379982566935759, "max": 0.11107556412781718, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.153363432114323, "min": 0.15309307855718274, "max": 0.4443022565112687, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.8269873112440109, "min": 0.820725101816888, "max": 2.789062142591266, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 3.3079492449760437, "min": 3.3079492449760437, "max": 13.19755872558145, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.045454545454547, "min": 3.340909090909091, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 147.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.340909090909091, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 147.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.3886687334161252, "min": 0.3886498395353556, "max": 0.6230454602871429, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 17.101424270309508, "min": 17.101424270309508, "max": 34.26750031579286, "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": "1673772800", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673773281" }, "total": 480.20971676, "count": 1, "self": 0.38876793199995063, "children": { "run_training.setup": { "total": 0.11121597800001837, "count": 1, "self": 0.11121597800001837 }, "TrainerController.start_learning": { "total": 479.70973285, "count": 1, "self": 0.5049015510062418, "children": { "TrainerController._reset_env": { "total": 9.351251915000006, "count": 1, "self": 9.351251915000006 }, "TrainerController.advance": { "total": 469.7244713999937, "count": 18210, "self": 0.26110751198871185, "children": { "env_step": { "total": 469.463363888005, "count": 18210, "self": 339.9411908210104, "children": { "SubprocessEnvManager._take_step": { "total": 129.26065375599913, "count": 18210, "self": 1.3711821340022823, "children": { "TorchPolicy.evaluate": { "total": 127.88947162199685, "count": 18210, "self": 31.032772800988198, "children": { "TorchPolicy.sample_actions": { "total": 96.85669882100865, "count": 18210, "self": 96.85669882100865 } } } } }, "workers": { "total": 0.2615193109954532, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 478.5769363529977, "count": 18210, "is_parallel": true, "self": 264.4768548789891, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006910314000009521, "count": 1, "is_parallel": true, "self": 0.0038533160000326916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030569979999768293, "count": 10, "is_parallel": true, "self": 0.0030569979999768293 } } }, "UnityEnvironment.step": { "total": 0.03437085000001616, "count": 1, "is_parallel": true, "self": 0.000529481000000942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003831160000231648, "count": 1, "is_parallel": true, "self": 0.0003831160000231648 }, "communicator.exchange": { "total": 0.03152460999999107, "count": 1, "is_parallel": true, "self": 0.03152460999999107 }, "steps_from_proto": { "total": 0.001933643000000984, "count": 1, "is_parallel": true, "self": 0.0004218749999438387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015117680000571454, "count": 10, "is_parallel": true, "self": 0.0015117680000571454 } } } } } } }, "UnityEnvironment.step": { "total": 214.1000814740086, "count": 18209, "is_parallel": true, "self": 8.386553065001351, "children": { "UnityEnvironment._generate_step_input": { "total": 5.165599907995386, "count": 18209, "is_parallel": true, "self": 5.165599907995386 }, "communicator.exchange": { "total": 169.99940403500602, "count": 18209, "is_parallel": true, "self": 169.99940403500602 }, "steps_from_proto": { "total": 30.54852446600583, "count": 18209, "is_parallel": true, "self": 6.45058908799902, "children": { "_process_rank_one_or_two_observation": { "total": 24.09793537800681, "count": 182090, "is_parallel": true, "self": 24.09793537800681 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.701900002146431e-05, "count": 1, "self": 4.701900002146431e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.2626303269913, "count": 281733, "is_parallel": true, "self": 7.539056527006267, "children": { "process_trajectory": { "total": 250.3354304219847, "count": 281733, "is_parallel": true, "self": 249.55120410998472, "children": { "RLTrainer._checkpoint": { "total": 0.784226311999987, "count": 4, "is_parallel": true, "self": 0.784226311999987 } } }, "_update_policy": { "total": 209.38814337800034, "count": 90, "is_parallel": true, "self": 45.01679542400328, "children": { "TorchPPOOptimizer.update": { "total": 164.37134795399706, "count": 4584, "is_parallel": true, "self": 164.37134795399706 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12906096500000785, "count": 1, "self": 0.0008667710000054285, "children": { "RLTrainer._checkpoint": { "total": 0.12819419400000243, "count": 1, "self": 0.12819419400000243 } } } } } } }