{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8168727159500122, "min": 0.8056074976921082, "max": 2.84737491607666, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7799.50048828125, "min": 7799.50048828125, "max": 29159.966796875, "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": 6.714617729187012, "min": 0.2590954601764679, "max": 6.714617729187012, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1309.3504638671875, "min": 50.26451873779297, "max": 1361.91845703125, "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": 0.0698590681229903, "min": 0.06157629102669364, "max": 0.07728244612271916, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2794362724919612, "min": 0.2672292279178281, "max": 0.36412036234761735, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14618440377799904, "min": 0.09518700041557096, "max": 0.20158036637539958, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5847376151119962, "min": 0.38074800166228384, "max": 1.007901831876998, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.616409730600001e-05, "min": 1.616409730600001e-05, "max": 0.0005837640027059999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.465638922400003e-05, "min": 6.465638922400003e-05, "max": 0.00277032003828, "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": 26.068181818181817, "min": 3.477272727272727, "max": 26.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 153.0, "max": 1455.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.477272727272727, "max": 26.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 153.0, "max": 1455.0, "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": "1682812050", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1682812513" }, "total": 463.1760118100001, "count": 1, "self": 0.4289063120004357, "children": { "run_training.setup": { "total": 0.03837099399993349, "count": 1, "self": 0.03837099399993349 }, "TrainerController.start_learning": { "total": 462.7087345039997, "count": 1, "self": 0.5385953640020489, "children": { "TrainerController._reset_env": { "total": 4.172746314999813, "count": 1, "self": 4.172746314999813 }, "TrainerController.advance": { "total": 457.8549318849982, "count": 18201, "self": 0.2550296910126235, "children": { "env_step": { "total": 457.5999021939856, "count": 18201, "self": 330.0173683849714, "children": { "SubprocessEnvManager._take_step": { "total": 127.3173148870028, "count": 18201, "self": 1.6640490720171783, "children": { "TorchPolicy.evaluate": { "total": 125.65326581498562, "count": 18201, "self": 125.65326581498562 } } }, "workers": { "total": 0.2652189220113996, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 461.2052560590121, "count": 18201, "is_parallel": true, "self": 219.11800254700552, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001698680999879798, "count": 1, "is_parallel": true, "self": 0.0004412959995079291, "children": { "_process_rank_one_or_two_observation": { "total": 0.001257385000371869, "count": 10, "is_parallel": true, "self": 0.001257385000371869 } } }, "UnityEnvironment.step": { "total": 0.06310810099989794, "count": 1, "is_parallel": true, "self": 0.0006132109997452062, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040094700011650275, "count": 1, "is_parallel": true, "self": 0.00040094700011650275 }, "communicator.exchange": { "total": 0.060244443000101455, "count": 1, "is_parallel": true, "self": 0.060244443000101455 }, "steps_from_proto": { "total": 0.0018494999999347783, "count": 1, "is_parallel": true, "self": 0.00034565299961286655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015038470003219118, "count": 10, "is_parallel": true, "self": 0.0015038470003219118 } } } } } } }, "UnityEnvironment.step": { "total": 242.08725351200655, "count": 18200, "is_parallel": true, "self": 9.050058720964898, "children": { "UnityEnvironment._generate_step_input": { "total": 5.328109216068242, "count": 18200, "is_parallel": true, "self": 5.328109216068242 }, "communicator.exchange": { "total": 196.14354363698885, "count": 18200, "is_parallel": true, "self": 196.14354363698885 }, "steps_from_proto": { "total": 31.565541937984563, "count": 18200, "is_parallel": true, "self": 6.067360436101808, "children": { "_process_rank_one_or_two_observation": { "total": 25.498181501882755, "count": 182000, "is_parallel": true, "self": 25.498181501882755 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010752199978014687, "count": 1, "self": 0.00010752199978014687, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.34726448795686, "count": 415525, "is_parallel": true, "self": 9.69620144298483, "children": { "process_trajectory": { "total": 248.06276390497283, "count": 415525, "is_parallel": true, "self": 247.29963225097322, "children": { "RLTrainer._checkpoint": { "total": 0.7631316539996078, "count": 4, "is_parallel": true, "self": 0.7631316539996078 } } }, "_update_policy": { "total": 196.5882991399992, "count": 90, "is_parallel": true, "self": 73.88801871199598, "children": { "TorchPPOOptimizer.update": { "total": 122.70028042800323, "count": 4587, "is_parallel": true, "self": 122.70028042800323 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1423534179998569, "count": 1, "self": 0.000910533000023861, "children": { "RLTrainer._checkpoint": { "total": 0.14144288499983304, "count": 1, "self": 0.14144288499983304 } } } } } } }