{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.931823492050171, "min": 1.931823492050171, "max": 3.295708656311035, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39934.65625, "min": 15912.376953125, "max": 134047.03125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 42.530434782608694, "min": 40.074380165289256, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19564.0, "min": 3996.0, "max": 30536.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1392.0737726668938, "min": 1197.001194479805, "max": 1410.1028201929319, "count": 480 }, "SoccerTwos.Self-play.ELO.sum": { "value": 320176.9677133856, "min": 2396.0910923381834, "max": 338264.64338618796, "count": 480 }, "SoccerTwos.Step.mean": { "value": 4999986.0, "min": 9030.0, "max": 4999986.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999986.0, "min": 9030.0, "max": 4999986.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.020223937928676605, "min": -0.0889531672000885, "max": 0.17569175362586975, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.631281852722168, "min": -20.281322479248047, "max": 32.8543586730957, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02101924456655979, "min": -0.08862104266881943, "max": 0.17977046966552734, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.813406944274902, "min": -20.205596923828125, "max": 33.6170768737793, "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": -0.09265327453613281, "min": -0.5882352941176471, "max": 0.4976159930229187, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.217599868774414, "min": -51.62679994106293, "max": 61.36760061979294, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09265327453613281, "min": -0.5882352941176471, "max": 0.4976159930229187, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.217599868774414, "min": -51.62679994106293, "max": 61.36760061979294, "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": 0.016220482345670462, "min": 0.010982282368543868, "max": 0.02318152036362638, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016220482345670462, "min": 0.010982282368543868, "max": 0.02318152036362638, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10962900544206301, "min": 1.2445342698204816e-05, "max": 0.11698166231314341, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10962900544206301, "min": 1.2445342698204816e-05, "max": 0.11698166231314341, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11299168641368548, "min": 1.2131652086585139e-05, "max": 0.11991602629423141, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11299168641368548, "min": 1.2131652086585139e-05, "max": 0.11991602629423141, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690658924", "python_version": "3.9.17 (main, Jul 5 2023, 16:17:03) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/eran/opt/anaconda3/envs/rl/bin/mlagents-learn /Users/eran/rl_course/ml-agents/config/poca/SoccerTwos.yaml --env=/Users/eran/rl_course/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos7 --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", "numpy_version": "1.21.2", "end_time_seconds": "1690681988" }, "total": 23063.798682286, "count": 1, "self": 0.7454080399984377, "children": { "run_training.setup": { "total": 0.03289832700000006, "count": 1, "self": 0.03289832700000006 }, "TrainerController.start_learning": { "total": 23063.020375919, "count": 1, "self": 7.038636560420855, "children": { "TrainerController._reset_env": { "total": 5.367032481000958, "count": 25, "self": 5.367032481000958 }, "TrainerController.advance": { "total": 23050.44275078758, "count": 336044, "self": 7.238345269568526, "children": { "env_step": { "total": 5254.720844670348, "count": 336044, "self": 4325.264234471794, "children": { "SubprocessEnvManager._take_step": { "total": 925.0752680246542, "count": 336044, "self": 41.21437040421495, "children": { "TorchPolicy.evaluate": { "total": 883.8608976204392, "count": 634836, "self": 883.8608976204392 } } }, "workers": { "total": 4.381342173899432, "count": 336044, "self": 0.0, "children": { "worker_root": { "total": 23046.73958037902, "count": 336044, "is_parallel": true, "self": 19536.17354361685, "children": { "steps_from_proto": { "total": 0.07485022300207511, "count": 50, "is_parallel": true, "self": 0.023650201003051485, "children": { "_process_rank_one_or_two_observation": { "total": 0.051200021999023626, "count": 200, "is_parallel": true, "self": 0.051200021999023626 } } }, "UnityEnvironment.step": { "total": 3510.4911865391687, "count": 336044, "is_parallel": true, "self": 204.17153747656357, "children": { "UnityEnvironment._generate_step_input": { "total": 120.79371196432899, "count": 336044, "is_parallel": true, "self": 120.79371196432899 }, "communicator.exchange": { "total": 2597.191372849924, "count": 336044, "is_parallel": true, "self": 2597.191372849924 }, "steps_from_proto": { "total": 588.3345642483523, "count": 672088, "is_parallel": true, "self": 121.10676272161152, "children": { "_process_rank_one_or_two_observation": { "total": 467.2278015267408, "count": 2688352, "is_parallel": true, "self": 467.2278015267408 } } } } } } } } } } }, "trainer_advance": { "total": 17788.483560847664, "count": 336044, "self": 52.8782545597096, "children": { "process_trajectory": { "total": 1572.0076158219758, "count": 336044, "self": 1569.918028740971, "children": { "RLTrainer._checkpoint": { "total": 2.0895870810047654, "count": 10, "self": 2.0895870810047654 } } }, "_update_policy": { "total": 16163.597690465978, "count": 238, "self": 787.0364935509697, "children": { "TorchPOCAOptimizer.update": { "total": 15376.561196915009, "count": 7152, "self": 15376.561196915009 } } } } } } }, "trainer_threads": { "total": 9.879986464511603e-07, "count": 1, "self": 9.879986464511603e-07 }, "TrainerController._save_models": { "total": 0.17195510199962882, "count": 1, "self": 0.003491924002446467, "children": { "RLTrainer._checkpoint": { "total": 0.16846317799718236, "count": 1, "self": 0.16846317799718236 } } } } } } }