{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8756429553031921, "min": 0.8593656420707703, "max": 2.84114146232605, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8938.5634765625, "min": 8243.03515625, "max": 29002.373046875, "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": 13.158675193786621, "min": 0.45054030418395996, "max": 13.158675193786621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2565.941650390625, "min": 86.0531997680664, "max": 2665.54638671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07410422843817037, "min": 0.057967368478043055, "max": 0.07467315050227769, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2964169137526815, "min": 0.24569042939601426, "max": 0.359067719732183, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18217703528410079, "min": 0.1538376708551511, "max": 0.27213079818323543, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7287081411364031, "min": 0.6153506834206044, "max": 1.3606539909161772, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.794097402e-06, "min": 7.794097402e-06, "max": 0.000291594002802, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.1176389608e-05, "min": 3.1176389608e-05, "max": 0.0013837200387599997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10259800000000002, "min": 0.10259800000000002, "max": 0.19719800000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4103920000000001, "min": 0.4103920000000001, "max": 0.9612400000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00013964020000000003, "min": 0.00013964020000000003, "max": 0.0048601802, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005585608000000001, "min": 0.0005585608000000001, "max": 0.023065875999999996, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.181818181818183, "min": 4.795454545454546, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1152.0, "min": 211.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.181818181818183, "min": 4.795454545454546, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1152.0, "min": 211.0, "max": 1411.0, "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": "1747492240", "python_version": "3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0]", "command_line_arguments": "/home/emanuele/miniconda3/envs/mlagents/bin/mlagents-learn /home/emanuele/Projects/ml-agents/config/ppo/SnowballTarget.yaml --env=./trained-env/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --resume", "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": "1747492455" }, "total": 215.1125194920005, "count": 1, "self": 0.21774217300117016, "children": { "run_training.setup": { "total": 0.027775348000432132, "count": 1, "self": 0.027775348000432132 }, "TrainerController.start_learning": { "total": 214.8670019709989, "count": 1, "self": 0.2292224710145092, "children": { "TrainerController._reset_env": { "total": 1.3673971320004057, "count": 1, "self": 1.3673971320004057 }, "TrainerController.advance": { "total": 213.2178821939833, "count": 18192, "self": 0.22068692109314725, "children": { "env_step": { "total": 141.88855539999895, "count": 18192, "self": 98.16271313912694, "children": { "SubprocessEnvManager._take_step": { "total": 43.587273086954156, "count": 18192, "self": 0.6589823949634592, "children": { "TorchPolicy.evaluate": { "total": 42.928290691990696, "count": 18192, "self": 42.928290691990696 } } }, "workers": { "total": 0.13856917391785828, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 214.46101288787213, "count": 18192, "is_parallel": true, "self": 129.7783942488404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010103370004799217, "count": 1, "is_parallel": true, "self": 0.00028784700225514825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007224899982247734, "count": 10, "is_parallel": true, "self": 0.0007224899982247734 } } }, "UnityEnvironment.step": { "total": 0.014677832999950624, "count": 1, "is_parallel": true, "self": 0.0002055830009339843, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015319500016630627, "count": 1, "is_parallel": true, "self": 0.00015319500016630627 }, "communicator.exchange": { "total": 0.013649169999553123, "count": 1, "is_parallel": true, "self": 0.013649169999553123 }, "steps_from_proto": { "total": 0.00066988499929721, "count": 1, "is_parallel": true, "self": 0.000158017996000126, "children": { "_process_rank_one_or_two_observation": { "total": 0.000511867003297084, "count": 10, "is_parallel": true, "self": 0.000511867003297084 } } } } } } }, "UnityEnvironment.step": { "total": 84.68261863903172, "count": 18191, "is_parallel": true, "self": 3.3021643408628734, "children": { "UnityEnvironment._generate_step_input": { "total": 1.976723401043273, "count": 18191, "is_parallel": true, "self": 1.976723401043273 }, "communicator.exchange": { "total": 68.3873693870155, "count": 18191, "is_parallel": true, "self": 68.3873693870155 }, "steps_from_proto": { "total": 11.016361510110073, "count": 18191, "is_parallel": true, "self": 2.392874241253594, "children": { "_process_rank_one_or_two_observation": { "total": 8.62348726885648, "count": 181910, "is_parallel": true, "self": 8.62348726885648 } } } } } } } } } } }, "trainer_advance": { "total": 71.10863987289122, "count": 18192, "self": 0.27175934183651407, "children": { "process_trajectory": { "total": 15.594262302052812, "count": 18192, "self": 15.304888923052204, "children": { "RLTrainer._checkpoint": { "total": 0.2893733790006081, "count": 4, "self": 0.2893733790006081 } } }, "_update_policy": { "total": 55.24261822900189, "count": 90, "self": 21.284006324965958, "children": { "TorchPPOOptimizer.update": { "total": 33.95861190403593, "count": 4587, "self": 33.95861190403593 } } } } } } }, "trainer_threads": { "total": 5.609999789157882e-07, "count": 1, "self": 5.609999789157882e-07 }, "TrainerController._save_models": { "total": 0.05249961300069117, "count": 1, "self": 0.0005349310013116337, "children": { "RLTrainer._checkpoint": { "total": 0.051964681999379536, "count": 1, "self": 0.051964681999379536 } } } } } } }