{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6328153610229492, "min": 0.6322746872901917, "max": 2.850437879562378, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6069.96484375, "min": 6069.96484375, "max": 29097.26953125, "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": 14.414107322692871, "min": 0.40153518319129944, "max": 14.448596954345703, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2954.89208984375, "min": 77.8978271484375, "max": 2961.96240234375, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06538399495041755, "min": 0.05965727009050383, "max": 0.0740971543303435, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3269199747520878, "min": 0.24185153652540653, "max": 0.37048577165171753, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1468094894699022, "min": 0.12143921858046716, "max": 0.32867359665094636, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7340474473495109, "min": 0.48575687432186865, "max": 1.6433679832547319, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "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": 28.4, "min": 3.5681818181818183, "max": 28.563636363636363, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1562.0, "min": 157.0, "max": 1571.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.4, "min": 3.5681818181818183, "max": 28.563636363636363, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1562.0, "min": 157.0, "max": 1571.0, "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": "1756376839", "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": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756378030" }, "total": 1191.100401277, "count": 1, "self": 0.4936445759999515, "children": { "run_training.setup": { "total": 0.027250564000041777, "count": 1, "self": 0.027250564000041777 }, "TrainerController.start_learning": { "total": 1190.579506137, "count": 1, "self": 1.0437216700013323, "children": { "TrainerController._reset_env": { "total": 3.384538836000047, "count": 1, "self": 3.384538836000047 }, "TrainerController.advance": { "total": 1186.0308631139985, "count": 45464, "self": 1.0450684769496092, "children": { "env_step": { "total": 819.5384782020012, "count": 45464, "self": 608.678274621027, "children": { "SubprocessEnvManager._take_step": { "total": 210.22957052997253, "count": 45464, "self": 3.3883061019614615, "children": { "TorchPolicy.evaluate": { "total": 206.84126442801107, "count": 45464, "self": 206.84126442801107 } } }, "workers": { "total": 0.6306330510017233, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1187.2463324000357, "count": 45464, "is_parallel": true, "self": 653.3888853000888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005266241000072114, "count": 1, "is_parallel": true, "self": 0.0038782159999755095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013880250000966043, "count": 10, "is_parallel": true, "self": 0.0013880250000966043 } } }, "UnityEnvironment.step": { "total": 0.03730906999999206, "count": 1, "is_parallel": true, "self": 0.0005802549997042661, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004167340000549302, "count": 1, "is_parallel": true, "self": 0.0004167340000549302 }, "communicator.exchange": { "total": 0.03440286600016407, "count": 1, "is_parallel": true, "self": 0.03440286600016407 }, "steps_from_proto": { "total": 0.001909215000068798, "count": 1, "is_parallel": true, "self": 0.0003682399997160246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015409750003527733, "count": 10, "is_parallel": true, "self": 0.0015409750003527733 } } } } } } }, "UnityEnvironment.step": { "total": 533.857447099947, "count": 45463, "is_parallel": true, "self": 24.73759757695143, "children": { "UnityEnvironment._generate_step_input": { "total": 14.070243677005692, "count": 45463, "is_parallel": true, "self": 14.070243677005692 }, "communicator.exchange": { "total": 412.45441507397027, "count": 45463, "is_parallel": true, "self": 412.45441507397027 }, "steps_from_proto": { "total": 82.59519077201958, "count": 45463, "is_parallel": true, "self": 15.063330805088981, "children": { "_process_rank_one_or_two_observation": { "total": 67.5318599669306, "count": 454630, "is_parallel": true, "self": 67.5318599669306 } } } } } } } } } } }, "trainer_advance": { "total": 365.4473164350477, "count": 45464, "self": 1.2714922570125964, "children": { "process_trajectory": { "total": 108.44685836103531, "count": 45464, "self": 107.01494003803509, "children": { "RLTrainer._checkpoint": { "total": 1.4319183230002182, "count": 10, "self": 1.4319183230002182 } } }, "_update_policy": { "total": 255.7289658169998, "count": 227, "self": 98.92171832201461, "children": { "TorchPPOOptimizer.update": { "total": 156.80724749498518, "count": 11574, "self": 156.80724749498518 } } } } } } }, "trainer_threads": { "total": 9.000000318337698e-07, "count": 1, "self": 9.000000318337698e-07 }, "TrainerController._save_models": { "total": 0.12038161700002092, "count": 1, "self": 0.0009293029997934354, "children": { "RLTrainer._checkpoint": { "total": 0.11945231400022749, "count": 1, "self": 0.11945231400022749 } } } } } } }