{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0893630981445312, "min": 1.0893630981445312, "max": 2.873898983001709, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10473.13671875, "min": 10473.13671875, "max": 29526.4375, "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": 12.847558975219727, "min": 0.3609851598739624, "max": 12.847558975219727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.27392578125, "min": 70.03112030029297, "max": 2618.2568359375, "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": 0.06617534235410144, "min": 0.061782237816934114, "max": 0.07413272489051737, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26470136941640576, "min": 0.2576225430980854, "max": 0.3461027801722772, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20788365613450022, "min": 0.11563206930854814, "max": 0.2926775203616011, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8315346245380009, "min": 0.46252827723419254, "max": 1.4633876018080056, "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": 25.022727272727273, "min": 3.3181818181818183, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 146.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.3181818181818183, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 146.0, "max": 1396.0, "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": "1698089717", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698090222" }, "total": 504.81754965499994, "count": 1, "self": 0.8050827519999189, "children": { "run_training.setup": { "total": 0.04451524600000312, "count": 1, "self": 0.04451524600000312 }, "TrainerController.start_learning": { "total": 503.967951657, "count": 1, "self": 0.6366341409997176, "children": { "TrainerController._reset_env": { "total": 8.166280992999987, "count": 1, "self": 8.166280992999987 }, "TrainerController.advance": { "total": 495.02974064600033, "count": 18218, "self": 0.3041908780061249, "children": { "env_step": { "total": 494.7255497679942, "count": 18218, "self": 337.4631680949872, "children": { "SubprocessEnvManager._take_step": { "total": 156.94506107101148, "count": 18218, "self": 1.5989868160064589, "children": { "TorchPolicy.evaluate": { "total": 155.34607425500502, "count": 18218, "self": 155.34607425500502 } } }, "workers": { "total": 0.3173206019955046, "count": 18218, "self": 0.0, "children": { "worker_root": { "total": 502.4610800339986, "count": 18218, "is_parallel": true, "self": 244.06312371798447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004864192000013645, "count": 1, "is_parallel": true, "self": 0.0033165690000487302, "children": { "_process_rank_one_or_two_observation": { "total": 0.001547622999964915, "count": 10, "is_parallel": true, "self": 0.001547622999964915 } } }, "UnityEnvironment.step": { "total": 0.04217129599999225, "count": 1, "is_parallel": true, "self": 0.0004979569999363775, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036636499999076477, "count": 1, "is_parallel": true, "self": 0.00036636499999076477 }, "communicator.exchange": { "total": 0.03928799700003083, "count": 1, "is_parallel": true, "self": 0.03928799700003083 }, "steps_from_proto": { "total": 0.0020189770000342833, "count": 1, "is_parallel": true, "self": 0.000389024000014615, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016299530000196683, "count": 10, "is_parallel": true, "self": 0.0016299530000196683 } } } } } } }, "UnityEnvironment.step": { "total": 258.39795631601413, "count": 18217, "is_parallel": true, "self": 11.356824634024235, "children": { "UnityEnvironment._generate_step_input": { "total": 6.0121599879982455, "count": 18217, "is_parallel": true, "self": 6.0121599879982455 }, "communicator.exchange": { "total": 203.5926234409954, "count": 18217, "is_parallel": true, "self": 203.5926234409954 }, "steps_from_proto": { "total": 37.436348252996254, "count": 18217, "is_parallel": true, "self": 7.080359347977208, "children": { "_process_rank_one_or_two_observation": { "total": 30.355988905019046, "count": 182170, "is_parallel": true, "self": 30.355988905019046 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001457690000279399, "count": 1, "self": 0.0001457690000279399, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.7367822330176, "count": 519856, "is_parallel": true, "self": 11.501928207977244, "children": { "process_trajectory": { "total": 280.20199823404045, "count": 519856, "is_parallel": true, "self": 279.2433789430405, "children": { "RLTrainer._checkpoint": { "total": 0.958619290999934, "count": 4, "is_parallel": true, "self": 0.958619290999934 } } }, "_update_policy": { "total": 199.03285579099992, "count": 90, "is_parallel": true, "self": 60.90381231799768, "children": { "TorchPPOOptimizer.update": { "total": 138.12904347300224, "count": 4587, "is_parallel": true, "self": 138.12904347300224 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13515010799994798, "count": 1, "self": 0.001256741999895894, "children": { "RLTrainer._checkpoint": { "total": 0.13389336600005208, "count": 1, "self": 0.13389336600005208 } } } } } } }