{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6763535141944885, "min": 0.5772567987442017, "max": 0.8170011043548584, "count": 81 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6904.216796875, "min": 573.7645263671875, "max": 8339.947265625, "count": 81 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 81 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 81 }, "SnowballTarget.Step.mean": { "value": 999992.0, "min": 209936.0, "max": 999992.0, "count": 80 }, "SnowballTarget.Step.sum": { "value": 999992.0, "min": 209936.0, "max": 999992.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.001880645751953, "min": 12.165338516235352, "max": 14.145326614379883, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2730.36669921875, "min": 2360.07568359375, "max": 2894.1689453125, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06619183858128963, "min": 0.06069366172442268, "max": 0.07497782197827417, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2647673543251585, "min": 0.2537285487541892, "max": 0.3705939667027754, "count": 80 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1689330839058932, "min": 0.1388872119725919, "max": 0.24017250216474717, "count": 80 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6757323356235728, "min": 0.5555488478903676, "max": 1.1725973995292889, "count": 80 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4412995196000008e-06, "min": 1.4412995196000008e-06, "max": 0.0002383812205396, "count": 80 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.765198078400003e-06, "min": 5.765198078400003e-06, "max": 0.001177056107648, "count": 80 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10048040000000001, "min": 0.10048040000000001, "max": 0.17946040000000002, "count": 80 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40192160000000005, "min": 0.40192160000000005, "max": 0.8923520000000001, "count": 80 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.397196000000001e-05, "min": 3.397196000000001e-05, "max": 0.00397507396, "count": 80 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013588784000000004, "min": 0.00013588784000000004, "max": 0.019628364800000003, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.613636363636363, "min": 24.636363636363637, "max": 27.945454545454545, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1215.0, "min": 1094.0, "max": 1537.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.613636363636363, "min": 24.636363636363637, "max": 27.945454545454545, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1215.0, "min": 1094.0, "max": 1537.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1771965495", "python_version": "3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]", "command_line_arguments": "/kaggle/working/mlagents-env/bin/mlagents-learn /kaggle/working/ml-agents/config/ppo/SnowballTarget.yaml --env=/kaggle/working/training-envs-executables/SnowballTarget/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1771966945" }, "total": 1450.027796929, "count": 1, "self": 0.3221737439998833, "children": { "run_training.setup": { "total": 0.01651180499993643, "count": 1, "self": 0.01651180499993643 }, "TrainerController.start_learning": { "total": 1449.6891113800002, "count": 1, "self": 1.357187974061162, "children": { "TrainerController._reset_env": { "total": 0.6131898730000103, "count": 1, "self": 0.6131898730000103 }, "TrainerController.advance": { "total": 1447.6450636579384, "count": 72792, "self": 1.3677062019378354, "children": { "env_step": { "total": 1015.8329502420947, "count": 72792, "self": 872.3113249719509, "children": { "SubprocessEnvManager._take_step": { "total": 142.66619366815667, "count": 72792, "self": 4.486886113172659, "children": { "TorchPolicy.evaluate": { "total": 138.179307554984, "count": 72792, "self": 138.179307554984 } } }, "workers": { "total": 0.8554316019872203, "count": 72792, "self": 0.0, "children": { "worker_root": { "total": 1446.8322269669934, "count": 72792, "is_parallel": true, "self": 678.0437214750955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024183679997804575, "count": 1, "is_parallel": true, "self": 0.0007359899982475326, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016823780015329248, "count": 10, "is_parallel": true, "self": 0.0016823780015329248 } } }, "UnityEnvironment.step": { "total": 0.02699791000031837, "count": 1, "is_parallel": true, "self": 0.00035739400027523516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042642500011425, "count": 1, "is_parallel": true, "self": 0.00042642500011425 }, "communicator.exchange": { "total": 0.02483729600044171, "count": 1, "is_parallel": true, "self": 0.02483729600044171 }, "steps_from_proto": { "total": 0.0013767949994871742, "count": 1, "is_parallel": true, "self": 0.00029327300126169575, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010835219982254785, "count": 10, "is_parallel": true, "self": 0.0010835219982254785 } } } } } } }, "UnityEnvironment.step": { "total": 768.7885054918979, "count": 72791, "is_parallel": true, "self": 36.33827272714916, "children": { "UnityEnvironment._generate_step_input": { "total": 20.0706446958784, "count": 72791, "is_parallel": true, "self": 20.0706446958784 }, "communicator.exchange": { "total": 592.0298332259263, "count": 72791, "is_parallel": true, "self": 592.0298332259263 }, "steps_from_proto": { "total": 120.3497548429441, "count": 72791, "is_parallel": true, "self": 21.73427093882492, "children": { "_process_rank_one_or_two_observation": { "total": 98.61548390411917, "count": 727910, "is_parallel": true, "self": 98.61548390411917 } } } } } } } } } } }, "trainer_advance": { "total": 430.44440721390583, "count": 72792, "self": 1.6056490339133234, "children": { "process_trajectory": { "total": 82.97671695698682, "count": 72792, "self": 82.55159718098639, "children": { "RLTrainer._checkpoint": { "total": 0.42511977600042883, "count": 5, "self": 0.42511977600042883 } } }, "_update_policy": { "total": 345.8620412230057, "count": 363, "self": 146.92715134594528, "children": { "TorchPPOOptimizer.update": { "total": 198.9348898770604, "count": 18510, "self": 198.9348898770604 } } } } } } }, "trainer_threads": { "total": 1.0020003173849545e-06, "count": 1, "self": 1.0020003173849545e-06 }, "TrainerController._save_models": { "total": 0.07366887300031522, "count": 1, "self": 0.0007980939999470138, "children": { "RLTrainer._checkpoint": { "total": 0.0728707790003682, "count": 1, "self": 0.0728707790003682 } } } } } } }