{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.201995611190796, "min": 2.173480272293091, "max": 2.314014196395874, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44674.0859375, "min": 37297.90234375, "max": 52114.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.52054794520548, "min": 54.666666666666664, "max": 93.9423076923077, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19132.0, "min": 18736.0, "max": 20684.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1501.2977191837756, "min": 1448.428316190716, "max": 1503.7782581484385, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 219189.46700083124, "min": 147811.67781677181, "max": 279689.9748241801, "count": 100 }, "SoccerTwos.Step.mean": { "value": 2999970.0, "min": 2009991.0, "max": 2999970.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 2999970.0, "min": 2009991.0, "max": 2999970.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07235688716173172, "min": -0.1096392348408699, "max": 0.09858974814414978, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.564105987548828, "min": -15.104362487792969, "max": 14.196924209594727, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07161447405815125, "min": -0.10906262695789337, "max": 0.10088992118835449, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.455713272094727, "min": -14.786467552185059, "max": 14.528148651123047, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07710684897148445, "min": -0.42398394241820286, "max": 0.2856749995715088, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.257599949836731, "min": -58.08580011129379, "max": 41.13719993829727, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07710684897148445, "min": -0.42398394241820286, "max": 0.2856749995715088, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.257599949836731, "min": -58.08580011129379, "max": 41.13719993829727, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020043744097711168, "min": 0.017251228770085923, "max": 0.03185359615987788, "count": 96 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020043744097711168, "min": 0.017251228770085923, "max": 0.03185359615987788, "count": 96 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1033657560745875, "min": 0.0701694172496597, "max": 0.1033657560745875, "count": 96 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1033657560745875, "min": 0.0701694172496597, "max": 0.1033657560745875, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10660624156395594, "min": 0.07164305417488019, "max": 0.10660624156395594, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10660624156395594, "min": 0.07164305417488019, "max": 0.10660624156395594, "count": 96 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 96 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 96 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 96 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 96 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 96 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 96 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718276835", "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/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718279378" }, "total": 2543.1800257669997, "count": 1, "self": 0.4459229669996603, "children": { "run_training.setup": { "total": 0.051663405999988754, "count": 1, "self": 0.051663405999988754 }, "TrainerController.start_learning": { "total": 2542.682439394, "count": 1, "self": 1.7609745530094187, "children": { "TrainerController._reset_env": { "total": 2.4089116700005206, "count": 6, "self": 2.4089116700005206 }, "TrainerController.advance": { "total": 2538.2034783439904, "count": 68323, "self": 1.7323525409487956, "children": { "env_step": { "total": 1754.4153196360703, "count": 68323, "self": 1334.566942097061, "children": { "SubprocessEnvManager._take_step": { "total": 418.84384843703094, "count": 68323, "self": 12.063535462993457, "children": { "TorchPolicy.evaluate": { "total": 406.7803129740375, "count": 125570, "self": 406.7803129740375 } } }, "workers": { "total": 1.0045291019783917, "count": 68323, "self": 0.0, "children": { "worker_root": { "total": 2537.1526747409644, "count": 68323, "is_parallel": true, "self": 1416.4915292459632, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033443359999978384, "count": 2, "is_parallel": true, "self": 0.0008517240000287529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024926119999690854, "count": 8, "is_parallel": true, "self": 0.0024926119999690854 } } }, "UnityEnvironment.step": { "total": 0.03887877500000059, "count": 1, "is_parallel": true, "self": 0.0011581419999515674, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008241240000188554, "count": 1, "is_parallel": true, "self": 0.0008241240000188554 }, "communicator.exchange": { "total": 0.03348753300002727, "count": 1, "is_parallel": true, "self": 0.03348753300002727 }, "steps_from_proto": { "total": 0.0034089760000028946, "count": 2, "is_parallel": true, "self": 0.0005874099998095517, "children": { "_process_rank_one_or_two_observation": { "total": 0.002821566000193343, "count": 8, "is_parallel": true, "self": 0.002821566000193343 } } } } } } }, "steps_from_proto": { "total": 0.009957218000010926, "count": 10, "is_parallel": true, "self": 0.0020800090006787286, "children": { "_process_rank_one_or_two_observation": { "total": 0.007877208999332197, "count": 40, "is_parallel": true, "self": 0.007877208999332197 } } }, "UnityEnvironment.step": { "total": 1120.6511882770012, "count": 68322, "is_parallel": true, "self": 69.13649921701744, "children": { "UnityEnvironment._generate_step_input": { "total": 45.612905000973626, "count": 68322, "is_parallel": true, "self": 45.612905000973626 }, "communicator.exchange": { "total": 788.4737009670148, "count": 68322, "is_parallel": true, "self": 788.4737009670148 }, "steps_from_proto": { "total": 217.42808309199535, "count": 136644, "is_parallel": true, "self": 36.7278482309996, "children": { "_process_rank_one_or_two_observation": { "total": 180.70023486099575, "count": 546576, "is_parallel": true, "self": 180.70023486099575 } } } } } } } } } } }, "trainer_advance": { "total": 782.0558061669711, "count": 68323, "self": 12.882832155030542, "children": { "process_trajectory": { "total": 215.49916042294052, "count": 68323, "self": 214.983963919941, "children": { "RLTrainer._checkpoint": { "total": 0.5151965029995154, "count": 2, "self": 0.5151965029995154 } } }, "_update_policy": { "total": 553.673813589, "count": 96, "self": 299.7714528620177, "children": { "TorchPOCAOptimizer.update": { "total": 253.9023607269823, "count": 5760, "self": 253.9023607269823 } } } } } } }, "trainer_threads": { "total": 8.130000423989259e-07, "count": 1, "self": 8.130000423989259e-07 }, "TrainerController._save_models": { "total": 0.3090740139996342, "count": 1, "self": 0.0040466209998157865, "children": { "RLTrainer._checkpoint": { "total": 0.3050273929998184, "count": 1, "self": 0.3050273929998184 } } } } } } }