{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5308985710144043, "min": 1.4465011358261108, "max": 3.2956511974334717, "count": 1048 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30030.10546875, "min": 7569.0537109375, "max": 116150.7109375, "count": 1048 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 75.02941176470588, "min": 39.75409836065574, "max": 999.0, "count": 1048 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20408.0, "min": 8592.0, "max": 31968.0, "count": 1048 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1534.6070552197643, "min": 1184.1629104376, "max": 1554.6191857663923, "count": 1041 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208706.55950988794, "min": 2373.017375252299, "max": 369763.2206767254, "count": 1041 }, "SoccerTwos.Step.mean": { "value": 10479986.0, "min": 9796.0, "max": 10479986.0, "count": 1048 }, "SoccerTwos.Step.sum": { "value": 10479986.0, "min": 9796.0, "max": 10479986.0, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012503576464951038, "min": -0.13079777359962463, "max": 0.1902237832546234, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.6879827976226807, "min": -25.527376174926758, "max": 25.78497314453125, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012296178378164768, "min": -0.1287485957145691, "max": 0.19197361171245575, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.6599841117858887, "min": -25.40910530090332, "max": 25.83808135986328, "count": 1048 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1048 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0225333328600283, "min": -0.6531499981880188, "max": 0.46796363626014104, "count": 1048 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.041999936103821, "min": -58.641600131988525, "max": 64.07880038022995, "count": 1048 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0225333328600283, "min": -0.6531499981880188, "max": 0.46796363626014104, "count": 1048 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.041999936103821, "min": -58.641600131988525, "max": 64.07880038022995, "count": 1048 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1048 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1048 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018268597793454924, "min": 0.010965228131196152, "max": 0.025365502247586845, "count": 506 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018268597793454924, "min": 0.010965228131196152, "max": 0.025365502247586845, "count": 506 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09751589621106783, "min": 0.0007242966231489037, "max": 0.13011609837412835, "count": 506 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09751589621106783, "min": 0.0007242966231489037, "max": 0.13011609837412835, "count": 506 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09897756576538086, "min": 0.0007508357440302563, "max": 0.13389939044912655, "count": 506 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09897756576538086, "min": 0.0007508357440302563, "max": 0.13389939044912655, "count": 506 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 506 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 506 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 506 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 506 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 506 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 506 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691279582", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/bbruno/miniconda3/envs/rl/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env=ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691327675" }, "total": 48093.438111874995, "count": 1, "self": 0.486673946994415, "children": { "run_training.setup": { "total": 0.013012811999942642, "count": 1, "self": 0.013012811999942642 }, "TrainerController.start_learning": { "total": 48092.938425116, "count": 1, "self": 19.758302727655973, "children": { "TrainerController._reset_env": { "total": 3.233504223935597, "count": 53, "self": 3.233504223935597 }, "TrainerController.advance": { "total": 48069.5043542084, "count": 723566, "self": 25.39068486460019, "children": { "env_step": { "total": 20053.8396527487, "count": 723566, "self": 17021.96302294438, "children": { "SubprocessEnvManager._take_step": { "total": 3018.8882173793245, "count": 723566, "self": 132.582089842399, "children": { "TorchPolicy.evaluate": { "total": 2886.3061275369255, "count": 1319970, "self": 2886.3061275369255 } } }, "workers": { "total": 12.988412424994749, "count": 723566, "self": 0.0, "children": { "worker_root": { "total": 48004.468154355716, "count": 723566, "is_parallel": true, "self": 33213.51954768781, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007175273007305805, "count": 2, "is_parallel": true, "self": 0.0022124130045995116, "children": { "_process_rank_one_or_two_observation": { "total": 0.004962860002706293, "count": 8, "is_parallel": true, "self": 0.004962860002706293 } } }, "UnityEnvironment.step": { "total": 0.051784895003947895, "count": 1, "is_parallel": true, "self": 0.0013205819996073842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005587560008279979, "count": 1, "is_parallel": true, "self": 0.0005587560008279979 }, "communicator.exchange": { "total": 0.04708239799947478, "count": 1, "is_parallel": true, "self": 0.04708239799947478 }, "steps_from_proto": { "total": 0.002823159004037734, "count": 2, "is_parallel": true, "self": 0.000489320998894982, "children": { "_process_rank_one_or_two_observation": { "total": 0.002333838005142752, "count": 8, "is_parallel": true, "self": 0.002333838005142752 } } } } } } }, "UnityEnvironment.step": { "total": 14790.781132599936, "count": 723565, "is_parallel": true, "self": 962.1630006595151, "children": { "UnityEnvironment._generate_step_input": { "total": 609.684037694693, "count": 723565, "is_parallel": true, "self": 609.684037694693 }, "communicator.exchange": { "total": 10672.25923538275, "count": 723565, "is_parallel": true, "self": 10672.25923538275 }, "steps_from_proto": { "total": 2546.674858862978, "count": 1447130, "is_parallel": true, "self": 473.68435492886056, "children": { "_process_rank_one_or_two_observation": { "total": 2072.9905039341174, "count": 5788520, "is_parallel": true, "self": 2072.9905039341174 } } } } }, "steps_from_proto": { "total": 0.16747406797367148, "count": 104, "is_parallel": true, "self": 0.03108669589710189, "children": { "_process_rank_one_or_two_observation": { "total": 0.1363873720765696, "count": 416, "is_parallel": true, "self": 0.1363873720765696 } } } } } } } } }, "trainer_advance": { "total": 27990.274016595104, "count": 723566, "self": 142.86888554311736, "children": { "process_trajectory": { "total": 5602.789371063089, "count": 723566, "self": 5595.425412840086, "children": { "RLTrainer._checkpoint": { "total": 7.363958223002555, "count": 20, "self": 7.363958223002555 } } }, "_update_policy": { "total": 22244.615759988897, "count": 507, "self": 1671.896190491323, "children": { "TorchPOCAOptimizer.update": { "total": 20572.719569497574, "count": 15213, "self": 20572.719569497574 } } } } } } }, "trainer_threads": { "total": 3.3520045690238476e-06, "count": 1, "self": 3.3520045690238476e-06 }, "TrainerController._save_models": { "total": 0.442260604002513, "count": 1, "self": 0.002804244009894319, "children": { "RLTrainer._checkpoint": { "total": 0.4394563599926187, "count": 1, "self": 0.4394563599926187 } } } } } } }