{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.294991970062256, "min": 3.294991970062256, "max": 3.295747995376587, "count": 3 }, "SoccerTwos.Policy.Entropy.sum": { "value": 59889.7734375, "min": 59889.7734375, "max": 105463.9375, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 619.5, "min": 492.5, "max": 885.75, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19824.0, "min": 11820.0, "max": 28344.0, "count": 3 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.2216125847149, "min": 1198.512895997199, "max": 1200.2216125847149, "count": 3 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12002.21612584715, "min": 4795.014370276737, "max": 12002.21612584715, "count": 3 }, "SoccerTwos.Step.mean": { "value": 29579.0, "min": 9188.0, "max": 29579.0, "count": 3 }, "SoccerTwos.Step.sum": { "value": 29579.0, "min": 9188.0, "max": 29579.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04330986738204956, "min": 0.04330986738204956, "max": 0.04582947865128517, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.692957878112793, "min": 0.5041242837905884, "max": 0.7332154512405396, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05042207986116409, "min": 0.04577548801898956, "max": 0.05042207986116409, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.8067532777786255, "min": 0.5035683512687683, "max": 0.8067532777786255, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08561250194907188, "min": -0.36363636363636365, "max": 0.11101250350475311, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.3698000311851501, "min": -4.0, "max": 1.7762000560760498, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08561250194907188, "min": -0.36363636363636365, "max": 0.11101250350475311, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.3698000311851501, "min": -4.0, "max": 1.7762000560760498, "count": 3 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0021249399287626147, "min": 0.0021249399287626147, "max": 0.0021249399287626147, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0021249399287626147, "min": 0.0021249399287626147, "max": 0.0021249399287626147, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.007496952001626293, "min": 0.007496952001626293, "max": 0.007496952001626293, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.007496952001626293, "min": 0.007496952001626293, "max": 0.007496952001626293, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004695787249753873, "min": 0.004695787249753873, "max": 0.004695787249753873, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004695787249753873, "min": 0.004695787249753873, "max": 0.004695787249753873, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717276638", "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:\\Users\\Jeste\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --torch-device cuda --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0", "numpy_version": "1.24.3", "end_time_seconds": "1717276694" }, "total": 55.94161929999973, "count": 1, "self": 0.005248999994364567, "children": { "run_training.setup": { "total": 0.07311640000261832, "count": 1, "self": 0.07311640000261832 }, "TrainerController.start_learning": { "total": 55.863253900002746, "count": 1, "self": 0.042421900034241844, "children": { "TrainerController._reset_env": { "total": 4.344175300000643, "count": 1, "self": 4.344175300000643 }, "TrainerController.advance": { "total": 51.28443339997466, "count": 2670, "self": 0.037352400344389025, "children": { "env_step": { "total": 43.60035759991297, "count": 2670, "self": 23.51200740026252, "children": { "SubprocessEnvManager._take_step": { "total": 20.063391899806447, "count": 2670, "self": 0.22031719956430607, "children": { "TorchPolicy.evaluate": { "total": 19.84307470024214, "count": 5318, "self": 19.84307470024214 } } }, "workers": { "total": 0.024958299844001886, "count": 2669, "self": 0.0, "children": { "worker_root": { "total": 52.217857700066816, "count": 2669, "is_parallel": true, "self": 33.69345090002753, "children": { "steps_from_proto": { "total": 0.0015405000012833625, "count": 2, "is_parallel": true, "self": 0.00031939999462338164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012211000066599809, "count": 8, "is_parallel": true, "self": 0.0012211000066599809 } } }, "UnityEnvironment.step": { "total": 18.522866300038004, "count": 2669, "is_parallel": true, "self": 1.0449094994692132, "children": { "UnityEnvironment._generate_step_input": { "total": 0.8874818002150278, "count": 2669, "is_parallel": true, "self": 0.8874818002150278 }, "communicator.exchange": { "total": 13.233655100215401, "count": 2669, "is_parallel": true, "self": 13.233655100215401 }, "steps_from_proto": { "total": 3.356819900138362, "count": 5338, "is_parallel": true, "self": 0.6450732003140729, "children": { "_process_rank_one_or_two_observation": { "total": 2.711746699824289, "count": 21352, "is_parallel": true, "self": 2.711746699824289 } } } } } } } } } } }, "trainer_advance": { "total": 7.6467233997173025, "count": 2669, "self": 0.2873427996528335, "children": { "process_trajectory": { "total": 3.6102151000668528, "count": 2669, "self": 3.6102151000668528 }, "_update_policy": { "total": 3.7491654999976163, "count": 1, "self": 2.3679731999945943, "children": { "TorchPOCAOptimizer.update": { "total": 1.381192300003022, "count": 3, "self": 1.381192300003022 } } } } } } }, "trainer_threads": { "total": 9.999930625781417e-07, "count": 1, "self": 9.999930625781417e-07 }, "TrainerController._save_models": { "total": 0.1922223000001395, "count": 1, "self": 0.0077162000015960075, "children": { "RLTrainer._checkpoint": { "total": 0.1845060999985435, "count": 1, "self": 0.1845060999985435 } } } } } } }