{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.275252342224121, "min": 2.275252342224121, "max": 3.2956926822662354, "count": 197 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45213.8125, "min": 27345.453125, "max": 105462.1640625, "count": 197 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.680851063829785, "min": 47.47, "max": 999.0, "count": 197 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19808.0, "min": 12556.0, "max": 31968.0, "count": 197 }, "SoccerTwos.Step.mean": { "value": 1979958.0, "min": 9000.0, "max": 1979958.0, "count": 198 }, "SoccerTwos.Step.sum": { "value": 1979958.0, "min": 9000.0, "max": 1979958.0, "count": 198 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.025730594992637634, "min": -0.11822260171175003, "max": 0.2088506817817688, "count": 198 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.8373517990112305, "min": -14.961146354675293, "max": 26.315185546875, "count": 198 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02415480464696884, "min": -0.12006423622369766, "max": 0.2116696834564209, "count": 198 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.541103363037109, "min": -14.156135559082031, "max": 26.670379638671875, "count": 198 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 198 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 198 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06313935905060869, "min": -0.5882352941176471, "max": 0.6639481518003676, "count": 198 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.870199501514435, "min": -59.55000019073486, "max": 71.7064003944397, "count": 198 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06313935905060869, "min": -0.5882352941176471, "max": 0.6639481518003676, "count": 198 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.870199501514435, "min": -59.55000019073486, "max": 71.7064003944397, "count": 198 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 198 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 198 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1473.1825463414482, "min": 1194.0034057009439, "max": 1473.1825463414482, "count": 196 }, "SoccerTwos.Self-play.ELO.sum": { "value": 276958.31871219224, "min": 2388.50241698197, "max": 303758.06167282234, "count": 196 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016436572575670046, "min": 0.011545663926517591, "max": 0.023501400930884604, "count": 94 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016436572575670046, "min": 0.011545663926517591, "max": 0.023501400930884604, "count": 94 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0995179792245229, "min": 0.0008222002851349923, "max": 0.10937345027923584, "count": 94 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0995179792245229, "min": 0.0008222002851349923, "max": 0.10937345027923584, "count": 94 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10111721629897753, "min": 0.0008312070118942453, "max": 0.11332893148064613, "count": 94 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10111721629897753, "min": 0.0008312070118942453, "max": 0.11332893148064613, "count": 94 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 94 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 94 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 94 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 94 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 94 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 94 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713530296", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/ixu/Desktop/Projects WIP/marl_soccer/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713531536" }, "total": 1240.4790082669351, "count": 1, "self": 0.04742303502280265, "children": { "run_training.setup": { "total": 0.007101755938492715, "count": 1, "self": 0.007101755938492715 }, "TrainerController.start_learning": { "total": 1240.4244834759738, "count": 1, "self": 1.1302310549654067, "children": { "TrainerController._reset_env": { "total": 0.7685058229835704, "count": 10, "self": 0.7685058229835704 }, "TrainerController.advance": { "total": 1238.4071374209598, "count": 133285, "self": 1.171209466876462, "children": { "env_step": { "total": 966.6317162554478, "count": 133285, "self": 719.107268515043, "children": { "SubprocessEnvManager._take_step": { "total": 246.7787815622287, "count": 133285, "self": 8.112934920587577, "children": { "TorchPolicy.evaluate": { "total": 238.6658466416411, "count": 251501, "self": 238.6658466416411 } } }, "workers": { "total": 0.7456661781761795, "count": 133284, "self": 0.0, "children": { "worker_root": { "total": 1238.8091836764943, "count": 133284, "is_parallel": true, "self": 651.9256760552526, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010363230248913169, "count": 2, "is_parallel": true, "self": 0.00023955409415066242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007967689307406545, "count": 8, "is_parallel": true, "self": 0.0007967689307406545 } } }, "UnityEnvironment.step": { "total": 0.013842551968991756, "count": 1, "is_parallel": true, "self": 0.0002746081445366144, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001937089255079627, "count": 1, "is_parallel": true, "self": 0.0001937089255079627 }, "communicator.exchange": { "total": 0.01269432797562331, "count": 1, "is_parallel": true, "self": 0.01269432797562331 }, "steps_from_proto": { "total": 0.0006799069233238697, "count": 2, "is_parallel": true, "self": 0.00013445387594401836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005454530473798513, "count": 8, "is_parallel": true, "self": 0.0005454530473798513 } } } } } } }, "UnityEnvironment.step": { "total": 586.8769371736562, "count": 133283, "is_parallel": true, "self": 32.728412658092566, "children": { "UnityEnvironment._generate_step_input": { "total": 20.463317427318543, "count": 133283, "is_parallel": true, "self": 20.463317427318543 }, "communicator.exchange": { "total": 443.9430830233032, "count": 133283, "is_parallel": true, "self": 443.9430830233032 }, "steps_from_proto": { "total": 89.74212406494189, "count": 266566, "is_parallel": true, "self": 16.447025579866022, "children": { "_process_rank_one_or_two_observation": { "total": 73.29509848507587, "count": 1066264, "is_parallel": true, "self": 73.29509848507587 } } } } }, "steps_from_proto": { "total": 0.00657044758554548, "count": 18, "is_parallel": true, "self": 0.001229763263836503, "children": { "_process_rank_one_or_two_observation": { "total": 0.005340684321708977, "count": 72, "is_parallel": true, "self": 0.005340684321708977 } } } } } } } } }, "trainer_advance": { "total": 270.6042116986355, "count": 133284, "self": 10.074312842800282, "children": { "process_trajectory": { "total": 111.07563559175469, "count": 133284, "self": 110.69107601267751, "children": { "RLTrainer._checkpoint": { "total": 0.38455957907717675, "count": 3, "self": 0.38455957907717675 } } }, "_update_policy": { "total": 149.4542632640805, "count": 95, "self": 96.65693989722058, "children": { "TorchPOCAOptimizer.update": { "total": 52.79732336685993, "count": 2862, "self": 52.79732336685993 } } } } } } }, "trainer_threads": { "total": 4.450557753443718e-07, "count": 1, "self": 4.450557753443718e-07 }, "TrainerController._save_models": { "total": 0.11860873200930655, "count": 1, "self": 0.0009553009876981378, "children": { "RLTrainer._checkpoint": { "total": 0.11765343102160841, "count": 1, "self": 0.11765343102160841 } } } } } } }