{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8119275569915771, "min": 1.8046886920928955, "max": 3.2957234382629395, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34383.13671875, "min": 26313.640625, "max": 137608.546875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.792682926829265, "min": 40.17213114754098, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19612.0, "min": 15392.0, "max": 24904.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1630.7772416397117, "min": 1196.6976399664054, "max": 1632.5201365988557, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 267447.4676289127, "min": 2394.05428930563, "max": 388915.07796660496, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999936.0, "min": 9468.0, "max": 4999936.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999936.0, "min": 9468.0, "max": 4999936.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04861421883106232, "min": -0.10762900859117508, "max": 0.23200660943984985, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.972731590270996, "min": -18.938650131225586, "max": 35.0771484375, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.048151645809412, "min": -0.1107553094625473, "max": 0.226263627409935, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.896869659423828, "min": -19.456939697265625, "max": 35.35406494140625, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.18004146290988457, "min": -0.5333333333333333, "max": 0.5658933301766713, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 29.52679991722107, "min": -50.23919975757599, "max": 57.35240042209625, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.18004146290988457, "min": -0.5333333333333333, "max": 0.5658933301766713, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 29.52679991722107, "min": -50.23919975757599, "max": 57.35240042209625, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.023950597116102774, "min": 0.011338669088824341, "max": 0.025320576528126065, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023950597116102774, "min": 0.011338669088824341, "max": 0.025320576528126065, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1157424787680308, "min": 0.00038813254116879155, "max": 0.1439566674331824, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1157424787680308, "min": 0.00038813254116879155, "max": 0.1439566674331824, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11698854143420855, "min": 0.0003902523618307896, "max": 0.1461903542280197, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11698854143420855, "min": 0.0003902523618307896, "max": 0.1461903542280197, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678182443", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "D:\\projects\\ml\\RL\\HuggingFace\\unit7\\ml-agents\\env2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu116", "numpy_version": "1.21.2", "end_time_seconds": "1678201526" }, "total": 19093.06664, "count": 1, "self": 2.022078500001953, "children": { "run_training.setup": { "total": 0.08788750000000012, "count": 1, "self": 0.08788750000000012 }, "TrainerController.start_learning": { "total": 19090.956673999997, "count": 1, "self": 11.382352699813055, "children": { "TrainerController._reset_env": { "total": 5.284118699998699, "count": 25, "self": 5.284118699998699 }, "TrainerController.advance": { "total": 19074.068643900187, "count": 344885, "self": 11.566200199693412, "children": { "env_step": { "total": 14689.248574000398, "count": 344885, "self": 7389.183730300782, "children": { "SubprocessEnvManager._take_step": { "total": 7293.030787500108, "count": 344885, "self": 75.14115099989613, "children": { "TorchPolicy.evaluate": { "total": 7217.889636500212, "count": 629658, "self": 7217.889636500212 } } }, "workers": { "total": 7.034056199507524, "count": 344885, "self": 0.0, "children": { "worker_root": { "total": 19070.123377200292, "count": 344885, "is_parallel": true, "self": 12989.002590901073, "children": { "steps_from_proto": { "total": 0.06264880000298723, "count": 50, "is_parallel": true, "self": 0.013333300015497596, "children": { "_process_rank_one_or_two_observation": { "total": 0.04931549998748963, "count": 200, "is_parallel": true, "self": 0.04931549998748963 } } }, "UnityEnvironment.step": { "total": 6081.058137499217, "count": 344885, "is_parallel": true, "self": 285.0361554999927, "children": { "UnityEnvironment._generate_step_input": { "total": 206.9657089995677, "count": 344885, "is_parallel": true, "self": 206.9657089995677 }, "communicator.exchange": { "total": 4676.430584999535, "count": 344885, "is_parallel": true, "self": 4676.430584999535 }, "steps_from_proto": { "total": 912.6256880001208, "count": 689770, "is_parallel": true, "self": 189.78555330028723, "children": { "_process_rank_one_or_two_observation": { "total": 722.8401346998336, "count": 2759080, "is_parallel": true, "self": 722.8401346998336 } } } } } } } } } } }, "trainer_advance": { "total": 4373.253869700096, "count": 344885, "self": 74.36921710055503, "children": { "process_trajectory": { "total": 2399.282026399519, "count": 344885, "self": 2395.3845925995183, "children": { "RLTrainer._checkpoint": { "total": 3.897433800000499, "count": 10, "self": 3.897433800000499 } } }, "_update_policy": { "total": 1899.602626200022, "count": 241, "self": 1061.1345908999747, "children": { "TorchPOCAOptimizer.update": { "total": 838.4680353000474, "count": 7239, "self": 838.4680353000474 } } } } } } }, "trainer_threads": { "total": 1.7000020307023078e-06, "count": 1, "self": 1.7000020307023078e-06 }, "TrainerController._save_models": { "total": 0.22155699999711942, "count": 1, "self": 0.0018910999970103148, "children": { "RLTrainer._checkpoint": { "total": 0.2196659000001091, "count": 1, "self": 0.2196659000001091 } } } } } } }