{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9206799268722534, "min": 0.9123677015304565, "max": 2.8675155639648438, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8800.779296875, "min": 8800.779296875, "max": 29366.2265625, "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": 12.81261920928955, "min": 0.5126653909683228, "max": 12.81261920928955, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.460693359375, "min": 99.45708465576172, "max": 2594.7666015625, "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.Losses.PolicyLoss.mean": { "value": 0.06614251207564867, "min": 0.0645576686239984, "max": 0.07646987594974537, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2645700483025947, "min": 0.2594024864734178, "max": 0.36738553077009994, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19700146795195694, "min": 0.11111410530101436, "max": 0.2758441340689566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7880058718078278, "min": 0.44445642120405743, "max": 1.379220670344783, "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.CumulativeReward.mean": { "value": 25.75, "min": 3.272727272727273, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 144.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.272727272727273, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 144.0, "max": 1393.0, "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": "1709006751", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709007218" }, "total": 466.29137721699993, "count": 1, "self": 0.43260808499996983, "children": { "run_training.setup": { "total": 0.05405732599996327, "count": 1, "self": 0.05405732599996327 }, "TrainerController.start_learning": { "total": 465.804711806, "count": 1, "self": 0.6706142669938799, "children": { "TrainerController._reset_env": { "total": 3.913575036999987, "count": 1, "self": 3.913575036999987 }, "TrainerController.advance": { "total": 461.12336688400615, "count": 18198, "self": 0.32076414599180225, "children": { "env_step": { "total": 460.80260273801434, "count": 18198, "self": 301.7543361750268, "children": { "SubprocessEnvManager._take_step": { "total": 158.71597416498662, "count": 18198, "self": 1.616765295985715, "children": { "TorchPolicy.evaluate": { "total": 157.0992088690009, "count": 18198, "self": 157.0992088690009 } } }, "workers": { "total": 0.33229239800090227, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 464.4867120749974, "count": 18198, "is_parallel": true, "self": 228.66628955300257, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005567324000026019, "count": 1, "is_parallel": true, "self": 0.0038812579999785157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016860660000475036, "count": 10, "is_parallel": true, "self": 0.0016860660000475036 } } }, "UnityEnvironment.step": { "total": 0.057698859000026914, "count": 1, "is_parallel": true, "self": 0.0007106190000172319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040852400002222566, "count": 1, "is_parallel": true, "self": 0.00040852400002222566 }, "communicator.exchange": { "total": 0.05354716900001222, "count": 1, "is_parallel": true, "self": 0.05354716900001222 }, "steps_from_proto": { "total": 0.0030325469999752386, "count": 1, "is_parallel": true, "self": 0.0003895390000252519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026430079999499867, "count": 10, "is_parallel": true, "self": 0.0026430079999499867 } } } } } } }, "UnityEnvironment.step": { "total": 235.82042252199483, "count": 18197, "is_parallel": true, "self": 11.245649515983928, "children": { "UnityEnvironment._generate_step_input": { "total": 5.570595125001489, "count": 18197, "is_parallel": true, "self": 5.570595125001489 }, "communicator.exchange": { "total": 184.4325632100053, "count": 18197, "is_parallel": true, "self": 184.4325632100053 }, "steps_from_proto": { "total": 34.57161467100411, "count": 18197, "is_parallel": true, "self": 6.674595932997477, "children": { "_process_rank_one_or_two_observation": { "total": 27.897018738006636, "count": 181970, "is_parallel": true, "self": 27.897018738006636 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018929899999875488, "count": 1, "self": 0.00018929899999875488, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 455.7214633540278, "count": 688560, "is_parallel": true, "self": 14.19929638198721, "children": { "process_trajectory": { "total": 251.0138054120403, "count": 688560, "is_parallel": true, "self": 250.63681556104024, "children": { "RLTrainer._checkpoint": { "total": 0.37698985100007576, "count": 3, "is_parallel": true, "self": 0.37698985100007576 } } }, "_update_policy": { "total": 190.50836156000025, "count": 90, "is_parallel": true, "self": 54.824734230006584, "children": { "TorchPPOOptimizer.update": { "total": 135.68362732999367, "count": 4584, "is_parallel": true, "self": 135.68362732999367 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0969663189999892, "count": 1, "self": 0.001052568999966752, "children": { "RLTrainer._checkpoint": { "total": 0.09591375000002245, "count": 1, "self": 0.09591375000002245 } } } } } } }