{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8546561002731323, "min": 0.8546561002731323, "max": 2.85563063621521, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8122.6513671875, "min": 8122.6513671875, "max": 29150.27734375, "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": 12.714407920837402, "min": 0.4686962068080902, "max": 12.714407920837402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2479.3095703125, "min": 90.92706298828125, "max": 2587.303955078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.060115935813918636, "min": 0.060115935813918636, "max": 0.07802549786637444, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24046374325567454, "min": 0.24046374325567454, "max": 0.39012748933187225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19193196771483798, "min": 0.13048414372857295, "max": 0.2911460938991285, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7677278708593519, "min": 0.5219365749142918, "max": 1.4557304694956423, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "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": 24.75, "min": 3.727272727272727, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 164.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 3.727272727272727, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 164.0, "max": 1398.0, "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": "1780619710", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn /content/ml-agents/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780620200" }, "total": 490.3454574560001, "count": 1, "self": 0.4816173090002849, "children": { "run_training.setup": { "total": 0.020863660000031814, "count": 1, "self": 0.020863660000031814 }, "TrainerController.start_learning": { "total": 489.84297648699976, "count": 1, "self": 0.424814153015177, "children": { "TrainerController._reset_env": { "total": 2.06697577200066, "count": 1, "self": 2.06697577200066 }, "TrainerController.advance": { "total": 487.25020427498384, "count": 18192, "self": 0.4547495141378022, "children": { "env_step": { "total": 359.5523092050353, "count": 18192, "self": 282.34378770995136, "children": { "SubprocessEnvManager._take_step": { "total": 76.96268965305717, "count": 18192, "self": 1.368848550169787, "children": { "TorchPolicy.evaluate": { "total": 75.59384110288738, "count": 18192, "self": 75.59384110288738 } } }, "workers": { "total": 0.24583184202674602, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 487.76915224694676, "count": 18192, "is_parallel": true, "self": 239.82979656803946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018400649987597717, "count": 1, "is_parallel": true, "self": 0.0005469429997901898, "children": { "_process_rank_one_or_two_observation": { "total": 0.001293121998969582, "count": 10, "is_parallel": true, "self": 0.001293121998969582 } } }, "UnityEnvironment.step": { "total": 0.040306995000719326, "count": 1, "is_parallel": true, "self": 0.0006051159998605726, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041399200017622206, "count": 1, "is_parallel": true, "self": 0.00041399200017622206 }, "communicator.exchange": { "total": 0.03742625700033386, "count": 1, "is_parallel": true, "self": 0.03742625700033386 }, "steps_from_proto": { "total": 0.0018616300003486685, "count": 1, "is_parallel": true, "self": 0.0003915030047210166, "children": { "_process_rank_one_or_two_observation": { "total": 0.001470126995627652, "count": 10, "is_parallel": true, "self": 0.001470126995627652 } } } } } } }, "UnityEnvironment.step": { "total": 247.9393556789073, "count": 18191, "is_parallel": true, "self": 11.14346420874972, "children": { "UnityEnvironment._generate_step_input": { "total": 6.040778374972433, "count": 18191, "is_parallel": true, "self": 6.040778374972433 }, "communicator.exchange": { "total": 189.64364169514556, "count": 18191, "is_parallel": true, "self": 189.64364169514556 }, "steps_from_proto": { "total": 41.11147140003959, "count": 18191, "is_parallel": true, "self": 7.181641125882379, "children": { "_process_rank_one_or_two_observation": { "total": 33.92983027415721, "count": 181910, "is_parallel": true, "self": 33.92983027415721 } } } } } } } } } } }, "trainer_advance": { "total": 127.24314555581077, "count": 18192, "self": 0.5139033206105523, "children": { "process_trajectory": { "total": 28.300443492193153, "count": 18192, "self": 27.83549157219204, "children": { "RLTrainer._checkpoint": { "total": 0.46495192000111274, "count": 4, "self": 0.46495192000111274 } } }, "_update_policy": { "total": 98.42879874300706, "count": 90, "self": 40.11947510208847, "children": { "TorchPPOOptimizer.update": { "total": 58.30932364091859, "count": 4587, "self": 58.30932364091859 } } } } } } }, "trainer_threads": { "total": 9.089999366551638e-07, "count": 1, "self": 9.089999366551638e-07 }, "TrainerController._save_models": { "total": 0.10098137800014229, "count": 1, "self": 0.0008166459992935415, "children": { "RLTrainer._checkpoint": { "total": 0.10016473200084874, "count": 1, "self": 0.10016473200084874 } } } } } } }