{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6046640872955322, "min": 0.5809189081192017, "max": 2.8379483222961426, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6172.4111328125, "min": 5553.84130859375, "max": 28969.77734375, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.935003280639648, "min": 0.4331207275390625, "max": 14.972412109375, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2912.32568359375, "min": 84.02542114257812, "max": 3055.17724609375, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.032520873723115074, "min": 0.02139378272962252, "max": 0.039632793032311986, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1300834948924603, "min": 0.08557513091849007, "max": 0.19816396516155993, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10008202726021409, "min": 0.10008202726021409, "max": 0.35671817511320114, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.40032810904085636, "min": 0.40032810904085636, "max": 1.5131584915022054, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3764995412000023e-06, "min": 1.3764995412000023e-06, "max": 0.00029837640054119997, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.505998164800009e-06, "min": 5.505998164800009e-06, "max": 0.001477032007656, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10045880000000001, "min": 0.10045880000000001, "max": 0.19945880000000002, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40183520000000006, "min": 0.40183520000000006, "max": 0.992344, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.289412000000005e-05, "min": 3.289412000000005e-05, "max": 0.00497299412, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0001315764800000002, "min": 0.0001315764800000002, "max": 0.0246179656, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 29.733333333333334, "min": 3.6818181818181817, "max": 29.733333333333334, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1338.0, "min": 162.0, "max": 1624.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 29.733333333333334, "min": 3.6818181818181817, "max": 29.733333333333334, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1338.0, "min": 162.0, "max": 1624.0, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741124112", "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=SnowballTarget5 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741126297" }, "total": 2184.4819171159997, "count": 1, "self": 0.4751641730008487, "children": { "run_training.setup": { "total": 0.021494432999134006, "count": 1, "self": 0.021494432999134006 }, "TrainerController.start_learning": { "total": 2183.9852585099998, "count": 1, "self": 1.7617365812266144, "children": { "TrainerController._reset_env": { "total": 2.0118533029999526, "count": 1, "self": 2.0118533029999526 }, "TrainerController.advance": { "total": 2179.579274817773, "count": 90928, "self": 1.844405148676742, "children": { "env_step": { "total": 1590.0935259330408, "count": 90928, "self": 1156.8052782602626, "children": { "SubprocessEnvManager._take_step": { "total": 432.1743347717793, "count": 90928, "self": 6.4066391177093465, "children": { "TorchPolicy.evaluate": { "total": 425.76769565406994, "count": 90928, "self": 425.76769565406994 } } }, "workers": { "total": 1.113912900998912, "count": 90928, "self": 0.0, "children": { "worker_root": { "total": 2176.7002558878876, "count": 90928, "is_parallel": true, "self": 1161.2251435198823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021309090006980114, "count": 1, "is_parallel": true, "self": 0.0006625349988098606, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014683740018881508, "count": 10, "is_parallel": true, "self": 0.0014683740018881508 } } }, "UnityEnvironment.step": { "total": 0.03779112400025042, "count": 1, "is_parallel": true, "self": 0.0006039820009391406, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043680799990397645, "count": 1, "is_parallel": true, "self": 0.00043680799990397645 }, "communicator.exchange": { "total": 0.03451568899981794, "count": 1, "is_parallel": true, "self": 0.03451568899981794 }, "steps_from_proto": { "total": 0.0022346449995893636, "count": 1, "is_parallel": true, "self": 0.00040954399810289033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018251010014864733, "count": 10, "is_parallel": true, "self": 0.0018251010014864733 } } } } } } }, "UnityEnvironment.step": { "total": 1015.4751123680053, "count": 90927, "is_parallel": true, "self": 48.28619834217261, "children": { "UnityEnvironment._generate_step_input": { "total": 27.520327178905063, "count": 90927, "is_parallel": true, "self": 27.520327178905063 }, "communicator.exchange": { "total": 779.0861997340371, "count": 90927, "is_parallel": true, "self": 779.0861997340371 }, "steps_from_proto": { "total": 160.5823871128905, "count": 90927, "is_parallel": true, "self": 28.509026324361912, "children": { "_process_rank_one_or_two_observation": { "total": 132.0733607885286, "count": 909270, "is_parallel": true, "self": 132.0733607885286 } } } } } } } } } } }, "trainer_advance": { "total": 587.6413437360552, "count": 90928, "self": 2.248193327007357, "children": { "process_trajectory": { "total": 259.7026438380535, "count": 90928, "self": 247.48320745705496, "children": { "RLTrainer._checkpoint": { "total": 12.219436380998559, "count": 20, "self": 12.219436380998559 } } }, "_update_policy": { "total": 325.69050657099433, "count": 454, "self": 190.89637654200396, "children": { "TorchPPOOptimizer.update": { "total": 134.79413002899037, "count": 5448, "self": 134.79413002899037 } } } } } } }, "trainer_threads": { "total": 9.180002962239087e-07, "count": 1, "self": 9.180002962239087e-07 }, "TrainerController._save_models": { "total": 0.6323928900001192, "count": 1, "self": 0.02648488399972848, "children": { "RLTrainer._checkpoint": { "total": 0.6059080060003907, "count": 1, "self": 0.6059080060003907 } } } } } } }