{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7822149991989136, "min": 1.7453781366348267, "max": 3.295663833618164, "count": 661 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38609.90625, "min": 10467.08984375, "max": 125354.65625, "count": 661 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 44.3177570093458, "min": 39.5, "max": 999.0, "count": 661 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18968.0, "min": 16328.0, "max": 24088.0, "count": 661 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1538.7605143129633, "min": 1178.5989668315106, "max": 1562.7509806582796, "count": 653 }, "SoccerTwos.Self-play.ELO.sum": { "value": 329294.75006297417, "min": 2361.174532664744, "max": 382318.7118468894, "count": 653 }, "SoccerTwos.Step.mean": { "value": 6609926.0, "min": 9068.0, "max": 6609926.0, "count": 661 }, "SoccerTwos.Step.sum": { "value": 6609926.0, "min": 9068.0, "max": 6609926.0, "count": 661 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.014761903323233128, "min": -0.12782159447669983, "max": 0.1758817881345749, "count": 661 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.173809289932251, "min": -27.737285614013672, "max": 25.6873779296875, "count": 661 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.012893281877040863, "min": -0.12705710530281067, "max": 0.1728358417749405, "count": 661 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.7720556259155273, "min": -27.571392059326172, "max": 26.044025421142578, "count": 661 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 661 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 661 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.024597209276154983, "min": -0.6153846153846154, "max": 0.40380740717605307, "count": 661 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.2883999943733215, "min": -55.9611998796463, "max": 60.58199977874756, "count": 661 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.024597209276154983, "min": -0.6153846153846154, "max": 0.40380740717605307, "count": 661 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.2883999943733215, "min": -55.9611998796463, "max": 60.58199977874756, "count": 661 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 661 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 661 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01707396974573688, "min": 0.010950594616588205, "max": 0.02413030941679608, "count": 318 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01707396974573688, "min": 0.010950594616588205, "max": 0.02413030941679608, "count": 318 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10570046529173852, "min": 0.0009495018108282238, "max": 0.13799785524606706, "count": 318 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10570046529173852, "min": 0.0009495018108282238, "max": 0.13799785524606706, "count": 318 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10721415902177493, "min": 0.000949964762548916, "max": 0.14026200572649639, "count": 318 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10721415902177493, "min": 0.000949964762548916, "max": 0.14026200572649639, "count": 318 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 318 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 318 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 318 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 318 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 318 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 318 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708950544", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\miniconda3\\envs\\ai-vs-ai\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1708969079" }, "total": 18534.7064361, "count": 1, "self": 0.14278510000440292, "children": { "run_training.setup": { "total": 0.10079140000016196, "count": 1, "self": 0.10079140000016196 }, "TrainerController.start_learning": { "total": 18534.462859599997, "count": 1, "self": 12.685384199059627, "children": { "TrainerController._reset_env": { "total": 6.546452300004603, "count": 34, "self": 6.546452300004603 }, "TrainerController.advance": { "total": 18515.087789400946, "count": 455140, "self": 12.294202002231032, "children": { "env_step": { "total": 8933.962382802936, "count": 455140, "self": 6972.291975398686, "children": { "SubprocessEnvManager._take_step": { "total": 1953.9903446055905, "count": 455140, "self": 66.39807941307663, "children": { "TorchPolicy.evaluate": { "total": 1887.5922651925139, "count": 833048, "self": 1887.5922651925139 } } }, "workers": { "total": 7.680062798659492, "count": 455140, "self": 0.0, "children": { "worker_root": { "total": 18512.59882730352, "count": 455140, "is_parallel": true, "self": 13013.635489304957, "children": { "steps_from_proto": { "total": 0.05948889988940209, "count": 68, "is_parallel": true, "self": 0.01309129988658242, "children": { "_process_rank_one_or_two_observation": { "total": 0.04639760000281967, "count": 272, "is_parallel": true, "self": 0.04639760000281967 } } }, "UnityEnvironment.step": { "total": 5498.903849098671, "count": 455140, "is_parallel": true, "self": 270.8469743872265, "children": { "UnityEnvironment._generate_step_input": { "total": 264.11067800105957, "count": 455140, "is_parallel": true, "self": 264.11067800105957 }, "communicator.exchange": { "total": 4060.5262949026583, "count": 455140, "is_parallel": true, "self": 4060.5262949026583 }, "steps_from_proto": { "total": 903.419901807727, "count": 910280, "is_parallel": true, "self": 190.2153265082161, "children": { "_process_rank_one_or_two_observation": { "total": 713.2045752995109, "count": 3641120, "is_parallel": true, "self": 713.2045752995109 } } } } } } } } } } }, "trainer_advance": { "total": 9568.83120459578, "count": 455140, "self": 82.52617349205684, "children": { "process_trajectory": { "total": 2069.552692403493, "count": 455140, "self": 2067.586379303524, "children": { "RLTrainer._checkpoint": { "total": 1.9663130999688292, "count": 13, "self": 1.9663130999688292 } } }, "_update_policy": { "total": 7416.752338700229, "count": 319, "self": 953.1598972998399, "children": { "TorchPOCAOptimizer.update": { "total": 6463.592441400389, "count": 9541, "self": 6463.592441400389 } } } } } } }, "trainer_threads": { "total": 1.6999983927235007e-06, "count": 1, "self": 1.6999983927235007e-06 }, "TrainerController._save_models": { "total": 0.14323199998761993, "count": 1, "self": 0.002328799993847497, "children": { "RLTrainer._checkpoint": { "total": 0.14090319999377243, "count": 1, "self": 0.14090319999377243 } } } } } } }