{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.745213747024536, "min": 2.744229316711426, "max": 2.8903398513793945, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4106.83984375, "min": 1932.4278564453125, "max": 4285.9609375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.6610846519470215, "min": -0.13039711117744446, "max": 1.6610846519470215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 43.188201904296875, "min": -2.0863537788391113, "max": 43.188201904296875, "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 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06050091581510417, "min": 0.06050091581510417, "max": 0.0862072527947306, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06050091581510417, "min": 0.06050091581510417, "max": 0.0862072527947306, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21537658046273625, "min": 0.07611152607326706, "max": 0.21537658046273625, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.21537658046273625, "min": 0.07611152607326706, "max": 0.21537658046273625, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.090909090909091, "min": 2.727272727272727, "max": 6.090909090909091, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 67.0, "min": 3.0, "max": 67.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.090909090909091, "min": 2.727272727272727, "max": 6.090909090909091, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 67.0, "min": 3.0, "max": 67.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748940998", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748941045" }, "total": 47.74102103600001, "count": 1, "self": 0.43361917599997923, "children": { "run_training.setup": { "total": 0.02250043599997298, "count": 1, "self": 0.02250043599997298 }, "TrainerController.start_learning": { "total": 47.284901424000054, "count": 1, "self": 0.03384538699856421, "children": { "TrainerController._reset_env": { "total": 3.1589053910000757, "count": 1, "self": 3.1589053910000757 }, "TrainerController.advance": { "total": 43.96093021300146, "count": 1864, "self": 0.04282001900389787, "children": { "env_step": { "total": 30.706137628001215, "count": 1864, "self": 23.254339909002965, "children": { "SubprocessEnvManager._take_step": { "total": 7.4313657899996315, "count": 1864, "self": 0.130267295002227, "children": { "TorchPolicy.evaluate": { "total": 7.3010984949974045, "count": 1864, "self": 7.3010984949974045 } } }, "workers": { "total": 0.020431928998618787, "count": 1864, "self": 0.0, "children": { "worker_root": { "total": 46.787629155002605, "count": 1864, "is_parallel": true, "self": 26.392337658007023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004996192000021438, "count": 1, "is_parallel": true, "self": 0.003429449000236673, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015667429997847648, "count": 10, "is_parallel": true, "self": 0.0015667429997847648 } } }, "UnityEnvironment.step": { "total": 0.036637963999964995, "count": 1, "is_parallel": true, "self": 0.0005665359999511566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004158599999755097, "count": 1, "is_parallel": true, "self": 0.0004158599999755097 }, "communicator.exchange": { "total": 0.03380221899999469, "count": 1, "is_parallel": true, "self": 0.03380221899999469 }, "steps_from_proto": { "total": 0.001853349000043636, "count": 1, "is_parallel": true, "self": 0.0003634480000300755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014899010000135604, "count": 10, "is_parallel": true, "self": 0.0014899010000135604 } } } } } } }, "UnityEnvironment.step": { "total": 20.395291496995583, "count": 1863, "is_parallel": true, "self": 0.9919147719912189, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5553709310017894, "count": 1863, "is_parallel": true, "self": 0.5553709310017894 }, "communicator.exchange": { "total": 15.64267938300236, "count": 1863, "is_parallel": true, "self": 15.64267938300236 }, "steps_from_proto": { "total": 3.2053264110002146, "count": 1863, "is_parallel": true, "self": 0.5720865570042406, "children": { "_process_rank_one_or_two_observation": { "total": 2.633239853995974, "count": 18630, "is_parallel": true, "self": 2.633239853995974 } } } } } } } } } } }, "trainer_advance": { "total": 13.211972565996348, "count": 1864, "self": 0.045814624996637576, "children": { "process_trajectory": { "total": 3.3185879899997417, "count": 1864, "self": 2.858603540999752, "children": { "RLTrainer._checkpoint": { "total": 0.4599844489999896, "count": 4, "self": 0.4599844489999896 } } }, "_update_policy": { "total": 9.847569950999969, "count": 9, "self": 3.9125530290006054, "children": { "TorchPPOOptimizer.update": { "total": 5.935016921999363, "count": 456, "self": 5.935016921999363 } } } } } } }, "trainer_threads": { "total": 1.2360000027911155e-06, "count": 1, "self": 1.2360000027911155e-06 }, "TrainerController._save_models": { "total": 0.13121919699995033, "count": 1, "self": 0.0008648020000237011, "children": { "RLTrainer._checkpoint": { "total": 0.13035439499992663, "count": 1, "self": 0.13035439499992663 } } } } } } }