{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9650673270225525, "min": 0.9650673270225525, "max": 2.8634374141693115, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9214.462890625, "min": 9214.462890625, "max": 29355.9609375, "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": 12.904330253601074, "min": 0.38179197907447815, "max": 12.904330253601074, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.344482421875, "min": 74.06764221191406, "max": 2605.8271484375, "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": 0.06411433918373066, "min": 0.06411433918373066, "max": 0.07438252525353878, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25645735673492265, "min": 0.25645735673492265, "max": 0.36467585486346205, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20818261911763866, "min": 0.12452945067529, "max": 0.2976185993528834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8327304764705546, "min": 0.49811780270116, "max": 1.446792440671547, "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": 25.65909090909091, "min": 3.090909090909091, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 136.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.090909090909091, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 136.0, "max": 1386.0, "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": "1690851360", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690851827" }, "total": 466.93745298000005, "count": 1, "self": 0.4324545669999793, "children": { "run_training.setup": { "total": 0.04380414400003474, "count": 1, "self": 0.04380414400003474 }, "TrainerController.start_learning": { "total": 466.46119426900003, "count": 1, "self": 0.5510317359975829, "children": { "TrainerController._reset_env": { "total": 6.737844198000005, "count": 1, "self": 6.737844198000005 }, "TrainerController.advance": { "total": 459.02973331800246, "count": 18201, "self": 0.26330481399446626, "children": { "env_step": { "total": 458.766428504008, "count": 18201, "self": 333.0490474900209, "children": { "SubprocessEnvManager._take_step": { "total": 125.44422566798443, "count": 18201, "self": 1.7038713999836546, "children": { "TorchPolicy.evaluate": { "total": 123.74035426800077, "count": 18201, "self": 123.74035426800077 } } }, "workers": { "total": 0.27315534600268165, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 464.9595424489982, "count": 18201, "is_parallel": true, "self": 221.8666391889866, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005403266999962852, "count": 1, "is_parallel": true, "self": 0.004003563999958715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013997030000041377, "count": 10, "is_parallel": true, "self": 0.0013997030000041377 } } }, "UnityEnvironment.step": { "total": 0.05886709599997175, "count": 1, "is_parallel": true, "self": 0.0005465129999606688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036635800000794916, "count": 1, "is_parallel": true, "self": 0.00036635800000794916 }, "communicator.exchange": { "total": 0.05633264499999768, "count": 1, "is_parallel": true, "self": 0.05633264499999768 }, "steps_from_proto": { "total": 0.0016215800000054514, "count": 1, "is_parallel": true, "self": 0.00042029100012541676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012012889998800347, "count": 10, "is_parallel": true, "self": 0.0012012889998800347 } } } } } } }, "UnityEnvironment.step": { "total": 243.0929032600116, "count": 18200, "is_parallel": true, "self": 10.420791022022684, "children": { "UnityEnvironment._generate_step_input": { "total": 5.165483239988589, "count": 18200, "is_parallel": true, "self": 5.165483239988589 }, "communicator.exchange": { "total": 193.39886446299738, "count": 18200, "is_parallel": true, "self": 193.39886446299738 }, "steps_from_proto": { "total": 34.10776453500296, "count": 18200, "is_parallel": true, "self": 6.21092876901082, "children": { "_process_rank_one_or_two_observation": { "total": 27.896835765992137, "count": 182000, "is_parallel": true, "self": 27.896835765992137 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011936600003537023, "count": 1, "self": 0.00011936600003537023, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 455.62504001403465, "count": 413824, "is_parallel": true, "self": 9.860647065053229, "children": { "process_trajectory": { "total": 248.30315966498182, "count": 413824, "is_parallel": true, "self": 247.5229340609818, "children": { "RLTrainer._checkpoint": { "total": 0.7802256040000088, "count": 4, "is_parallel": true, "self": 0.7802256040000088 } } }, "_update_policy": { "total": 197.4612332839996, "count": 90, "is_parallel": true, "self": 77.46145680599949, "children": { "TorchPPOOptimizer.update": { "total": 119.99977647800011, "count": 4587, "is_parallel": true, "self": 119.99977647800011 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14246565099995223, "count": 1, "self": 0.0009052509999492031, "children": { "RLTrainer._checkpoint": { "total": 0.14156040000000303, "count": 1, "self": 0.14156040000000303 } } } } } } }