{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1662611961364746, "min": 1.1662611961364746, "max": 2.8611679077148438, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11135.4619140625, "min": 11135.4619140625, "max": 29332.693359375, "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": 12.428703308105469, "min": 0.35668379068374634, "max": 12.428703308105469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2423.59716796875, "min": 69.1966552734375, "max": 2513.271484375, "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": 0.06026895807693054, "min": 0.06026895807693054, "max": 0.0740331245138118, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24107583230772217, "min": 0.24107583230772217, "max": 0.37016562256905905, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20805378952154926, "min": 0.11242406598038918, "max": 0.2862101056266065, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8322151580861971, "min": 0.4496962639215567, "max": 1.3548536274363012, "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": 24.727272727272727, "min": 3.3181818181818183, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 146.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.3181818181818183, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 146.0, "max": 1345.0, "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": "1675344261", "python_version": "3.9.2 (default, Feb 28 2021, 17:03:44) \n[GCC 10.2.1 20210110]", "command_line_arguments": "/home/olav/dev/python/hug-rl/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.0", "end_time_seconds": "1675344669" }, "total": 407.81601024300016, "count": 1, "self": 0.3204813310003374, "children": { "run_training.setup": { "total": 0.015708887999608123, "count": 1, "self": 0.015708887999608123 }, "TrainerController.start_learning": { "total": 407.4798200240002, "count": 1, "self": 0.696593027056224, "children": { "TrainerController._reset_env": { "total": 0.7398178429994005, "count": 1, "self": 0.7398178429994005 }, "TrainerController.advance": { "total": 405.95579459194414, "count": 18204, "self": 0.37549311893417325, "children": { "env_step": { "total": 405.58030147300997, "count": 18204, "self": 308.3815203889262, "children": { "SubprocessEnvManager._take_step": { "total": 96.84380461899036, "count": 18204, "self": 1.6821978800080615, "children": { "TorchPolicy.evaluate": { "total": 95.1616067389823, "count": 18204, "self": 13.197995755970624, "children": { "TorchPolicy.sample_actions": { "total": 81.96361098301168, "count": 18204, "self": 81.96361098301168 } } } } }, "workers": { "total": 0.35497646509338665, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 406.59362366494497, "count": 18204, "is_parallel": true, "self": 178.434302886948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001477494999562623, "count": 1, "is_parallel": true, "self": 0.0004141019981034333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010633930014591897, "count": 10, "is_parallel": true, "self": 0.0010633930014591897 } } }, "UnityEnvironment.step": { "total": 0.041202341999451164, "count": 1, "is_parallel": true, "self": 0.0005665069993483485, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005424789997050539, "count": 1, "is_parallel": true, "self": 0.0005424789997050539 }, "communicator.exchange": { "total": 0.03817544600042311, "count": 1, "is_parallel": true, "self": 0.03817544600042311 }, "steps_from_proto": { "total": 0.001917909999974654, "count": 1, "is_parallel": true, "self": 0.00047059600001375657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014473139999608975, "count": 10, "is_parallel": true, "self": 0.0014473139999608975 } } } } } } }, "UnityEnvironment.step": { "total": 228.15932077799698, "count": 18203, "is_parallel": true, "self": 9.970444253203823, "children": { "UnityEnvironment._generate_step_input": { "total": 8.343786343943975, "count": 18203, "is_parallel": true, "self": 8.343786343943975 }, "communicator.exchange": { "total": 178.2304511028915, "count": 18203, "is_parallel": true, "self": 178.2304511028915 }, "steps_from_proto": { "total": 31.61463907795769, "count": 18203, "is_parallel": true, "self": 7.632101192280061, "children": { "_process_rank_one_or_two_observation": { "total": 23.98253788567763, "count": 182030, "is_parallel": true, "self": 23.98253788567763 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001740890002110973, "count": 1, "self": 0.0001740890002110973, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 404.7388965471664, "count": 202584, "is_parallel": true, "self": 4.42287842711994, "children": { "process_trajectory": { "total": 228.55206522804656, "count": 202584, "is_parallel": true, "self": 227.75059013504688, "children": { "RLTrainer._checkpoint": { "total": 0.8014750929996808, "count": 4, "is_parallel": true, "self": 0.8014750929996808 } } }, "_update_policy": { "total": 171.7639528919999, "count": 90, "is_parallel": true, "self": 30.63024234099612, "children": { "TorchPPOOptimizer.update": { "total": 141.1337105510038, "count": 4587, "is_parallel": true, "self": 141.1337105510038 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08744047300024249, "count": 1, "self": 0.0008018159996936447, "children": { "RLTrainer._checkpoint": { "total": 0.08663865700054885, "count": 1, "self": 0.08663865700054885 } } } } } } }