{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2430670261383057, "min": 3.236278772354126, "max": 3.2957499027252197, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 60710.21484375, "min": 2203.65869140625, "max": 105464.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 876.0, "min": 601.5, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17520.0, "min": 14436.0, "max": 28236.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.9250461637996, "min": 1199.028413043959, "max": 1201.9250461637996, "count": 9 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4807.700184655198, "min": 4799.298291225256, "max": 14401.389580399295, "count": 9 }, "SoccerTwos.Step.mean": { "value": 99622.0, "min": 9134.0, "max": 99622.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99622.0, "min": 9134.0, "max": 99622.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05494840070605278, "min": -0.10753211379051208, "max": -0.05494840070605278, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.6044324040412903, "min": -1.612935185432434, "max": -0.6044324040412903, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.055799081921577454, "min": -0.1076042428612709, "max": -0.055799081921577454, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.6137899160385132, "min": -1.613857388496399, "max": -0.6137899160385132, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14489090984517877, "min": -0.42857142857142855, "max": 0.3165428510734013, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.5938000082969666, "min": -6.0, "max": 4.431599915027618, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14489090984517877, "min": -0.42857142857142855, "max": 0.3165428510734013, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.5938000082969666, "min": -6.0, "max": 4.431599915027618, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014994360304748018, "min": 0.01270702642117006, "max": 0.018770560765794166, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014994360304748018, "min": 0.01270702642117006, "max": 0.018770560765794166, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.004776931647211313, "min": 0.00199684277176857, "max": 0.004776931647211313, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.004776931647211313, "min": 0.00199684277176857, "max": 0.004776931647211313, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004814004067641994, "min": 0.0020025838166475296, "max": 0.004814004067641994, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004814004067641994, "min": 0.0020025838166475296, "max": 0.004814004067641994, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715931561", "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/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1715931857" }, "total": 296.27023903400004, "count": 1, "self": 0.22055799800091336, "children": { "run_training.setup": { "total": 0.03282997499991325, "count": 1, "self": 0.03282997499991325 }, "TrainerController.start_learning": { "total": 296.0168510609992, "count": 1, "self": 0.13051113399524183, "children": { "TrainerController._reset_env": { "total": 7.55948712099962, "count": 1, "self": 7.55948712099962 }, "TrainerController.advance": { "total": 287.7771383990039, "count": 6733, "self": 0.1411887439480779, "children": { "env_step": { "total": 254.85827018500459, "count": 6733, "self": 95.7878528169349, "children": { "SubprocessEnvManager._take_step": { "total": 158.9781465360329, "count": 6733, "self": 0.8890426069492605, "children": { "TorchPolicy.evaluate": { "total": 158.08910392908365, "count": 13386, "self": 158.08910392908365 } } }, "workers": { "total": 0.09227083203677466, "count": 6733, "self": 0.0, "children": { "worker_root": { "total": 295.01171056897874, "count": 6733, "is_parallel": true, "self": 214.66559205099657, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005202803000429412, "count": 2, "is_parallel": true, "self": 0.0021000780006943387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031027249997350737, "count": 8, "is_parallel": true, "self": 0.0031027249997350737 } } }, "UnityEnvironment.step": { "total": 0.024671509000654623, "count": 1, "is_parallel": true, "self": 0.00042789300186996115, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029958199957036413, "count": 1, "is_parallel": true, "self": 0.00029958199957036413 }, "communicator.exchange": { "total": 0.02259016499920108, "count": 1, "is_parallel": true, "self": 0.02259016499920108 }, "steps_from_proto": { "total": 0.0013538690000132192, "count": 2, "is_parallel": true, "self": 0.00028276100056245923, "children": { "_process_rank_one_or_two_observation": { "total": 0.00107110799945076, "count": 8, "is_parallel": true, "self": 0.00107110799945076 } } } } } } }, "UnityEnvironment.step": { "total": 80.34611851798218, "count": 6732, "is_parallel": true, "self": 2.672641663047216, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6190366220253054, "count": 6732, "is_parallel": true, "self": 1.6190366220253054 }, "communicator.exchange": { "total": 68.29776480096189, "count": 6732, "is_parallel": true, "self": 68.29776480096189 }, "steps_from_proto": { "total": 7.7566754319477695, "count": 13464, "is_parallel": true, "self": 1.775871663887301, "children": { "_process_rank_one_or_two_observation": { "total": 5.980803768060468, "count": 53856, "is_parallel": true, "self": 5.980803768060468 } } } } } } } } } } }, "trainer_advance": { "total": 32.777679470051226, "count": 6733, "self": 0.9283729919989128, "children": { "process_trajectory": { "total": 13.535963981052191, "count": 6733, "self": 13.535963981052191 }, "_update_policy": { "total": 18.31334249700012, "count": 4, "self": 8.098787536007876, "children": { "TorchPOCAOptimizer.update": { "total": 10.214554960992245, "count": 120, "self": 10.214554960992245 } } } } } } }, "trainer_threads": { "total": 8.480001270072535e-07, "count": 1, "self": 8.480001270072535e-07 }, "TrainerController._save_models": { "total": 0.5497135590003381, "count": 1, "self": 0.005970064000393904, "children": { "RLTrainer._checkpoint": { "total": 0.5437434949999442, "count": 1, "self": 0.5437434949999442 } } } } } } }