{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7318130135536194, "min": 0.7157538533210754, "max": 2.8470075130462646, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7019.55029296875, "min": 6802.52490234375, "max": 29062.25390625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.883004188537598, "min": 0.44007959961891174, "max": 13.963363647460938, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2846.015869140625, "min": 85.37544250488281, "max": 2857.1767578125, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06883126503870537, "min": 0.06582636786782721, "max": 0.07339388498483138, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3441563251935269, "min": 0.2634149495827253, "max": 0.35694785964151377, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15535483804695746, "min": 0.12603965677622267, "max": 0.263959777815377, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7767741902347873, "min": 0.5041586271048907, "max": 1.2917528364588233, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000023e-06, "min": 3.0528989824000023e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.526449491200001e-05, "min": 1.526449491200001e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.4119904000000001, "max": 0.9846880000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.077824000000005e-05, "min": 6.077824000000005e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030389120000000027, "min": 0.00030389120000000027, "max": 0.024235931200000005, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.527272727272727, "min": 4.159090909090909, "max": 27.57777777777778, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1514.0, "min": 183.0, "max": 1514.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.527272727272727, "min": 4.159090909090909, "max": 27.57777777777778, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1514.0, "min": 183.0, "max": 1514.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1746529616", "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": "1746531138" }, "total": 1521.4296559050001, "count": 1, "self": 0.6471418829996765, "children": { "run_training.setup": { "total": 0.02278916500017658, "count": 1, "self": 0.02278916500017658 }, "TrainerController.start_learning": { "total": 1520.7597248570003, "count": 1, "self": 0.7991563549730927, "children": { "TrainerController._reset_env": { "total": 3.5552240960000745, "count": 1, "self": 3.5552240960000745 }, "TrainerController.advance": { "total": 1516.2892561990268, "count": 45464, "self": 0.8460767659985322, "children": { "env_step": { "total": 707.3346640440327, "count": 45464, "self": 539.4484405659557, "children": { "SubprocessEnvManager._take_step": { "total": 167.40929125099956, "count": 45464, "self": 2.9757321230085836, "children": { "TorchPolicy.evaluate": { "total": 164.43355912799097, "count": 45464, "self": 164.43355912799097 } } }, "workers": { "total": 0.476932227077441, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1517.956370631003, "count": 45464, "is_parallel": true, "self": 1043.899227301023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005421593000164648, "count": 1, "is_parallel": true, "self": 0.003998612999794204, "children": { "_process_rank_one_or_two_observation": { "total": 0.001422980000370444, "count": 10, "is_parallel": true, "self": 0.001422980000370444 } } }, "UnityEnvironment.step": { "total": 0.03564988999983143, "count": 1, "is_parallel": true, "self": 0.0005879850000383158, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037606599994433054, "count": 1, "is_parallel": true, "self": 0.00037606599994433054 }, "communicator.exchange": { "total": 0.03284156199993049, "count": 1, "is_parallel": true, "self": 0.03284156199993049 }, "steps_from_proto": { "total": 0.0018442769999182929, "count": 1, "is_parallel": true, "self": 0.00036646200032919296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014778149995891, "count": 10, "is_parallel": true, "self": 0.0014778149995891 } } } } } } }, "UnityEnvironment.step": { "total": 474.0571433299799, "count": 45463, "is_parallel": true, "self": 23.554720656971313, "children": { "UnityEnvironment._generate_step_input": { "total": 13.467158528986602, "count": 45463, "is_parallel": true, "self": 13.467158528986602 }, "communicator.exchange": { "total": 361.8902350760245, "count": 45463, "is_parallel": true, "self": 361.8902350760245 }, "steps_from_proto": { "total": 75.14502906799748, "count": 45463, "is_parallel": true, "self": 13.239886421908295, "children": { "_process_rank_one_or_two_observation": { "total": 61.90514264608919, "count": 454630, "is_parallel": true, "self": 61.90514264608919 } } } } } } } } } } }, "trainer_advance": { "total": 808.1085153889956, "count": 45464, "self": 0.9415400460220553, "children": { "process_trajectory": { "total": 64.11215596597458, "count": 45464, "self": 63.26986769997461, "children": { "RLTrainer._checkpoint": { "total": 0.8422882659999686, "count": 10, "self": 0.8422882659999686 } } }, "_update_policy": { "total": 743.0548193769989, "count": 227, "self": 296.0849816109603, "children": { "TorchPPOOptimizer.update": { "total": 446.9698377660386, "count": 38580, "self": 446.9698377660386 } } } } } } }, "trainer_threads": { "total": 1.1440001799201127e-06, "count": 1, "self": 1.1440001799201127e-06 }, "TrainerController._save_models": { "total": 0.11608706300012273, "count": 1, "self": 0.000780648999807454, "children": { "RLTrainer._checkpoint": { "total": 0.11530641400031527, "count": 1, "self": 0.11530641400031527 } } } } } } }