{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.3297736644744873, "min": 2.3108389377593994, "max": 3.2958154678344727, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46893.68359375, "min": 19817.169921875, "max": 160233.140625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.91954022988506, "min": 43.35087719298246, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19808.0, "min": 14648.0, "max": 25348.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1534.3269811293542, "min": 1183.5485215813121, "max": 1551.405389093557, "count": 480 }, "SoccerTwos.Self-play.ELO.sum": { "value": 266972.89471650764, "min": 2367.0970431626242, "max": 341892.72860558936, "count": 480 }, "SoccerTwos.Step.mean": { "value": 4999939.0, "min": 9690.0, "max": 4999939.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999939.0, "min": 9690.0, "max": 4999939.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00910065695643425, "min": -0.09789004176855087, "max": 0.23074674606323242, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.5835143327713013, "min": -14.487726211547852, "max": 35.30425262451172, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.008705869317054749, "min": -0.09969667345285416, "max": 0.23732972145080566, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.5148212909698486, "min": -14.755107879638672, "max": 36.31144714355469, "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": 0.03772988538632448, "min": -0.5714285714285714, "max": 0.3872978086889225, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.565000057220459, "min": -49.93519985675812, "max": 60.75959986448288, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.03772988538632448, "min": -0.5714285714285714, "max": 0.3872978086889225, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.565000057220459, "min": -49.93519985675812, "max": 60.75959986448288, "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": 0.016802129296896357, "min": 0.01020057471760083, "max": 0.022905385214835407, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016802129296896357, "min": 0.01020057471760083, "max": 0.022905385214835407, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10920455977320671, "min": 1.278151113600264e-06, "max": 0.11705219199260077, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10920455977320671, "min": 1.278151113600264e-06, "max": 0.11705219199260077, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11106214225292206, "min": 1.2946513142727176e-06, "max": 0.11790347720185916, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11106214225292206, "min": 1.2946513142727176e-06, "max": 0.11790347720185916, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.999999999999999e-05, "min": 4.999999999999999e-05, "max": 5e-05, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.999999999999999e-05, "min": 4.999999999999999e-05, "max": 5e-05, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703425867", "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/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703431621" }, "total": 5753.9713630119995, "count": 1, "self": 10.003901086998667, "children": { "run_training.setup": { "total": 0.03320010800052842, "count": 1, "self": 0.03320010800052842 }, "TrainerController.start_learning": { "total": 5743.934261817, "count": 1, "self": 4.598700764327077, "children": { "TrainerController._reset_env": { "total": 2.461793570003465, "count": 25, "self": 2.461793570003465 }, "TrainerController.advance": { "total": 5736.68472627367, "count": 336279, "self": 4.452538133902635, "children": { "env_step": { "total": 3768.169735152508, "count": 336279, "self": 2540.511554829661, "children": { "SubprocessEnvManager._take_step": { "total": 1225.00736433792, "count": 336279, "self": 27.384061780176125, "children": { "TorchPolicy.evaluate": { "total": 1197.623302557744, "count": 636948, "self": 1197.623302557744 } } }, "workers": { "total": 2.650815984927249, "count": 336279, "self": 0.0, "children": { "worker_root": { "total": 5738.468630533378, "count": 336279, "is_parallel": true, "self": 3703.546075526435, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022654249996776343, "count": 2, "is_parallel": true, "self": 0.0011427790004745475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011226459992030868, "count": 8, "is_parallel": true, "self": 0.0011226459992030868 } } }, "UnityEnvironment.step": { "total": 0.017416921999938495, "count": 1, "is_parallel": true, "self": 0.0006658129987044958, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006755950007573119, "count": 1, "is_parallel": true, "self": 0.0006755950007573119 }, "communicator.exchange": { "total": 0.014058880999982648, "count": 1, "is_parallel": true, "self": 0.014058880999982648 }, "steps_from_proto": { "total": 0.002016633000494039, "count": 2, "is_parallel": true, "self": 0.00039346100038528675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016231720001087524, "count": 8, "is_parallel": true, "self": 0.0016231720001087524 } } } } } } }, "UnityEnvironment.step": { "total": 2034.8957418499367, "count": 336278, "is_parallel": true, "self": 115.62528190730063, "children": { "UnityEnvironment._generate_step_input": { "total": 83.27074140703007, "count": 336278, "is_parallel": true, "self": 83.27074140703007 }, "communicator.exchange": { "total": 1483.7842008194802, "count": 336278, "is_parallel": true, "self": 1483.7842008194802 }, "steps_from_proto": { "total": 352.21551771612576, "count": 672556, "is_parallel": true, "self": 73.3906903016632, "children": { "_process_rank_one_or_two_observation": { "total": 278.82482741446256, "count": 2690224, "is_parallel": true, "self": 278.82482741446256 } } } } }, "steps_from_proto": { "total": 0.026813157006472466, "count": 48, "is_parallel": true, "self": 0.005673642001966073, "children": { "_process_rank_one_or_two_observation": { "total": 0.021139515004506393, "count": 192, "is_parallel": true, "self": 0.021139515004506393 } } } } } } } } }, "trainer_advance": { "total": 1964.0624529872593, "count": 336279, "self": 34.067328851527236, "children": { "process_trajectory": { "total": 543.9419646267424, "count": 336279, "self": 541.9494062307422, "children": { "RLTrainer._checkpoint": { "total": 1.9925583960002768, "count": 10, "self": 1.9925583960002768 } } }, "_update_policy": { "total": 1386.0531595089897, "count": 237, "self": 423.7020367749792, "children": { "TorchPOCAOptimizer.update": { "total": 962.3511227340105, "count": 7116, "self": 962.3511227340105 } } } } } } }, "trainer_threads": { "total": 5.279998731566593e-07, "count": 1, "self": 5.279998731566593e-07 }, "TrainerController._save_models": { "total": 0.18904068099982396, "count": 1, "self": 0.0012437099994713208, "children": { "RLTrainer._checkpoint": { "total": 0.18779697100035264, "count": 1, "self": 0.18779697100035264 } } } } } } }