{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0714858770370483, "min": 1.0714858770370483, "max": 2.860839605331421, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10289.478515625, "min": 10289.478515625, "max": 29392.265625, "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": 12.125568389892578, "min": 0.41120776534080505, "max": 12.125568389892578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2364.48583984375, "min": 79.77430725097656, "max": 2457.4404296875, "count": 20 }, "SnowballTarget.Policy.RndValueEstimate.mean": { "value": 0.007355439942330122, "min": 0.0019533310551196337, "max": 0.2565062344074249, "count": 20 }, "SnowballTarget.Policy.RndValueEstimate.sum": { "value": 1.434310793876648, "min": 0.40043288469314575, "max": 52.583778381347656, "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": 0.06906518266266942, "min": 0.063120017402552, "max": 0.07591321173808241, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2762607306506777, "min": 0.252480069610208, "max": 0.37250734032953486, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.11007115847485907, "min": 0.06702082138736823, "max": 0.14513722926962608, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4402846338994363, "min": 0.2680832855494729, "max": 0.7256861463481304, "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.RNDLoss.mean": { "value": 0.0045647150836884975, "min": 0.0045647150836884975, "max": 0.5318121910095215, "count": 20 }, "SnowballTarget.Losses.RNDLoss.sum": { "value": 0.01825886033475399, "min": 0.01825886033475399, "max": 2.127248764038086, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.204545454545453, "min": 3.5454545454545454, "max": 24.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1065.0, "min": 156.0, "max": 1322.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.204545454545453, "min": 3.5454545454545454, "max": 24.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1065.0, "min": 156.0, "max": 1322.0, "count": 20 }, "SnowballTarget.Policy.RndReward.mean": { "value": 0.009373288976679429, "min": 0.009373288976679429, "max": 1.343559264903888, "count": 20 }, "SnowballTarget.Policy.RndReward.sum": { "value": 0.4124247149738949, "min": 0.4124247149738949, "max": 59.11660765577108, "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": "1718031381", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718031881" }, "total": 499.8885199829999, "count": 1, "self": 0.4340388900000107, "children": { "run_training.setup": { "total": 0.056039202999954796, "count": 1, "self": 0.056039202999954796 }, "TrainerController.start_learning": { "total": 499.39844188999996, "count": 1, "self": 0.6075577049994081, "children": { "TrainerController._reset_env": { "total": 2.9251674150000326, "count": 1, "self": 2.9251674150000326 }, "TrainerController.advance": { "total": 495.7655167000005, "count": 18207, "self": 0.29095706897692253, "children": { "env_step": { "total": 495.47455963102357, "count": 18207, "self": 339.22200804403224, "children": { "SubprocessEnvManager._take_step": { "total": 155.95805763499334, "count": 18207, "self": 1.5136530989807397, "children": { "TorchPolicy.evaluate": { "total": 154.4444045360126, "count": 18207, "self": 154.4444045360126 } } }, "workers": { "total": 0.29449395199799255, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 498.180288759989, "count": 18207, "is_parallel": true, "self": 267.7599729829942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006065234000061537, "count": 1, "is_parallel": true, "self": 0.0042560290000892564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018092049999722803, "count": 10, "is_parallel": true, "self": 0.0018092049999722803 } } }, "UnityEnvironment.step": { "total": 0.037206079000043246, "count": 1, "is_parallel": true, "self": 0.0006477679999079555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043884399997295986, "count": 1, "is_parallel": true, "self": 0.00043884399997295986 }, "communicator.exchange": { "total": 0.03413452700010566, "count": 1, "is_parallel": true, "self": 0.03413452700010566 }, "steps_from_proto": { "total": 0.0019849400000566675, "count": 1, "is_parallel": true, "self": 0.0003771510005208256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016077889995358419, "count": 10, "is_parallel": true, "self": 0.0016077889995358419 } } } } } } }, "UnityEnvironment.step": { "total": 230.4203157769948, "count": 18206, "is_parallel": true, "self": 10.5559268710158, "children": { "UnityEnvironment._generate_step_input": { "total": 5.577089681994039, "count": 18206, "is_parallel": true, "self": 5.577089681994039 }, "communicator.exchange": { "total": 179.22171612699663, "count": 18206, "is_parallel": true, "self": 179.22171612699663 }, "steps_from_proto": { "total": 35.06558309698835, "count": 18206, "is_parallel": true, "self": 6.699808945920495, "children": { "_process_rank_one_or_two_observation": { "total": 28.365774151067853, "count": 182060, "is_parallel": true, "self": 28.365774151067853 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001641430001200206, "count": 1, "self": 0.0001641430001200206, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.7068229459667, "count": 624682, "is_parallel": true, "self": 13.287378819008836, "children": { "process_trajectory": { "total": 268.7078037889596, "count": 624682, "is_parallel": true, "self": 267.9846450489599, "children": { "RLTrainer._checkpoint": { "total": 0.7231587399996897, "count": 4, "is_parallel": true, "self": 0.7231587399996897 } } }, "_update_policy": { "total": 208.71164033799823, "count": 90, "is_parallel": true, "self": 97.93833124199864, "children": { "TorchPPOOptimizer.update": { "total": 110.7733090959996, "count": 4587, "is_parallel": true, "self": 110.7733090959996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10003592699990804, "count": 1, "self": 0.0009241979998932948, "children": { "RLTrainer._checkpoint": { "total": 0.09911172900001475, "count": 1, "self": 0.09911172900001475 } } } } } } }