{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9319132566452026, "min": 0.9319132566452026, "max": 2.870424747467041, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8938.912109375, "min": 8938.912109375, "max": 29522.318359375, "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": 12.874151229858398, "min": 0.39834508299827576, "max": 12.874151229858398, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.45947265625, "min": 77.27894592285156, "max": 2602.755126953125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06857709564963657, "min": 0.057933525650250714, "max": 0.07610024299595833, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2743083825985463, "min": 0.23173410260100286, "max": 0.38050121497979167, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17977972606233525, "min": 0.10100476959761343, "max": 0.28556475897922234, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.719118904249341, "min": 0.4040190783904537, "max": 1.408571179006614, "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": 25.363636363636363, "min": 3.1136363636363638, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 137.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.1136363636363638, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 137.0, "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": "1721472628", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1721473081" }, "total": 453.7232466909918, "count": 1, "self": 0.2725397319882177, "children": { "run_training.setup": { "total": 0.013106368016451597, "count": 1, "self": 0.013106368016451597 }, "TrainerController.start_learning": { "total": 453.43760059098713, "count": 1, "self": 0.4767339399259072, "children": { "TrainerController._reset_env": { "total": 2.856478811998386, "count": 1, "self": 2.856478811998386 }, "TrainerController.advance": { "total": 450.0170217230916, "count": 18207, "self": 0.2265568540606182, "children": { "env_step": { "total": 449.790464869031, "count": 18207, "self": 262.4828545647615, "children": { "SubprocessEnvManager._take_step": { "total": 187.07232962345006, "count": 18207, "self": 1.2606316194287501, "children": { "TorchPolicy.evaluate": { "total": 185.8116980040213, "count": 18207, "self": 185.8116980040213 } } }, "workers": { "total": 0.23528068081941456, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 452.63578140575555, "count": 18207, "is_parallel": true, "self": 268.31014963949565, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011406879930291325, "count": 1, "is_parallel": true, "self": 0.0003602970391511917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007803909538779408, "count": 10, "is_parallel": true, "self": 0.0007803909538779408 } } }, "UnityEnvironment.step": { "total": 0.035801211022771895, "count": 1, "is_parallel": true, "self": 0.00043541903141885996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012463539896998554, "count": 1, "is_parallel": true, "self": 0.0012463539896998554 }, "communicator.exchange": { "total": 0.032584517990471795, "count": 1, "is_parallel": true, "self": 0.032584517990471795 }, "steps_from_proto": { "total": 0.0015349200111813843, "count": 1, "is_parallel": true, "self": 0.00049385498277843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010410650284029543, "count": 10, "is_parallel": true, "self": 0.0010410650284029543 } } } } } } }, "UnityEnvironment.step": { "total": 184.3256317662599, "count": 18206, "is_parallel": true, "self": 4.547100880125072, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7601509311934933, "count": 18206, "is_parallel": true, "self": 2.7601509311934933 }, "communicator.exchange": { "total": 162.79889808109147, "count": 18206, "is_parallel": true, "self": 162.79889808109147 }, "steps_from_proto": { "total": 14.219481873849872, "count": 18206, "is_parallel": true, "self": 3.3427517008967698, "children": { "_process_rank_one_or_two_observation": { "total": 10.876730172953103, "count": 182060, "is_parallel": true, "self": 10.876730172953103 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001153459888882935, "count": 1, "self": 0.0001153459888882935, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.1581348279433, "count": 372741, "is_parallel": true, "self": 5.601814194989856, "children": { "process_trajectory": { "total": 245.7939493758895, "count": 372741, "is_parallel": true, "self": 245.11395980493398, "children": { "RLTrainer._checkpoint": { "total": 0.679989570955513, "count": 4, "is_parallel": true, "self": 0.679989570955513 } } }, "_update_policy": { "total": 196.76237125706393, "count": 90, "is_parallel": true, "self": 30.571620423404966, "children": { "TorchPPOOptimizer.update": { "total": 166.19075083365897, "count": 4587, "is_parallel": true, "self": 166.19075083365897 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08725076998234726, "count": 1, "self": 0.0015113929694052786, "children": { "RLTrainer._checkpoint": { "total": 0.08573937701294199, "count": 1, "self": 0.08573937701294199 } } } } } } }