{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.007369875907898, "min": 1.007369875907898, "max": 2.8627476692199707, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9651.611328125, "min": 9651.611328125, "max": 29380.37890625, "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": 12.96635913848877, "min": 0.4874587953090668, "max": 12.96635913848877, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.43994140625, "min": 94.56700897216797, "max": 2635.32861328125, "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": 0.0688643287176805, "min": 0.06193108791024619, "max": 0.07274467173088388, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.275457314870722, "min": 0.26305817724285446, "max": 0.3637233586544194, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20009962717692056, "min": 0.12357156358513177, "max": 0.29836983785909765, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8003985087076823, "min": 0.4942862543405271, "max": 1.4918491892954884, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.347009730600001e-05, "min": 1.347009730600001e-05, "max": 0.00048647000270600005, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.388038922400004e-05, "min": 5.388038922400004e-05, "max": 0.00230860003828, "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": 25.90909090909091, "min": 3.7954545454545454, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 167.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.7954545454545454, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 167.0, "max": 1396.0, "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": "1723820511", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1723821148" }, "total": 636.9300958519998, "count": 1, "self": 0.6488304839999728, "children": { "run_training.setup": { "total": 0.10882747300001938, "count": 1, "self": 0.10882747300001938 }, "TrainerController.start_learning": { "total": 636.1724378949998, "count": 1, "self": 0.8398506239882408, "children": { "TrainerController._reset_env": { "total": 3.7584479769998325, "count": 1, "self": 3.7584479769998325 }, "TrainerController.advance": { "total": 631.4566146660118, "count": 18204, "self": 0.46293312908710504, "children": { "env_step": { "total": 630.9936815369247, "count": 18204, "self": 483.45581824486317, "children": { "SubprocessEnvManager._take_step": { "total": 147.1102492969767, "count": 18204, "self": 2.522112096026831, "children": { "TorchPolicy.evaluate": { "total": 144.58813720094986, "count": 18204, "self": 144.58813720094986 } } }, "workers": { "total": 0.4276139950848119, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 634.329694492988, "count": 18204, "is_parallel": true, "self": 314.1689605490383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026370000000497384, "count": 1, "is_parallel": true, "self": 0.0007953039998938038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018416960001559346, "count": 10, "is_parallel": true, "self": 0.0018416960001559346 } } }, "UnityEnvironment.step": { "total": 0.04883597500020187, "count": 1, "is_parallel": true, "self": 0.0007591520006826613, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004533149999588204, "count": 1, "is_parallel": true, "self": 0.0004533149999588204 }, "communicator.exchange": { "total": 0.04506395499993232, "count": 1, "is_parallel": true, "self": 0.04506395499993232 }, "steps_from_proto": { "total": 0.0025595529996280675, "count": 1, "is_parallel": true, "self": 0.000497399998948822, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020621530006792455, "count": 10, "is_parallel": true, "self": 0.0020621530006792455 } } } } } } }, "UnityEnvironment.step": { "total": 320.1607339439497, "count": 18203, "is_parallel": true, "self": 14.686577079979088, "children": { "UnityEnvironment._generate_step_input": { "total": 7.7479958559843, "count": 18203, "is_parallel": true, "self": 7.7479958559843 }, "communicator.exchange": { "total": 247.79607702002068, "count": 18203, "is_parallel": true, "self": 247.79607702002068 }, "steps_from_proto": { "total": 49.930083987965645, "count": 18203, "is_parallel": true, "self": 9.617159973949583, "children": { "_process_rank_one_or_two_observation": { "total": 40.31292401401606, "count": 182030, "is_parallel": true, "self": 40.31292401401606 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015068999982759124, "count": 1, "self": 0.00015068999982759124, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 623.868845456032, "count": 808409, "is_parallel": true, "self": 19.701947340667175, "children": { "process_trajectory": { "total": 321.63743359936325, "count": 808409, "is_parallel": true, "self": 320.46038986336407, "children": { "RLTrainer._checkpoint": { "total": 1.1770437359991774, "count": 4, "is_parallel": true, "self": 1.1770437359991774 } } }, "_update_policy": { "total": 282.52946451600155, "count": 90, "is_parallel": true, "self": 79.28684527897803, "children": { "TorchPPOOptimizer.update": { "total": 203.24261923702352, "count": 4587, "is_parallel": true, "self": 203.24261923702352 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11737393800012796, "count": 1, "self": 0.0022767869995732326, "children": { "RLTrainer._checkpoint": { "total": 0.11509715100055473, "count": 1, "self": 0.11509715100055473 } } } } } } }