{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.995697021484375, "min": 1.9803928136825562, "max": 3.2957608699798584, "count": 504 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39850.078125, "min": 18725.2734375, "max": 106288.3359375, "count": 504 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.59340659340659, "min": 41.69230769230769, "max": 999.0, "count": 504 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19508.0, "min": 16416.0, "max": 23676.0, "count": 504 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1484.2542645087476, "min": 1173.5653248572992, "max": 1502.3933503229662, "count": 486 }, "SoccerTwos.Self-play.ELO.sum": { "value": 270134.27614059206, "min": 2363.566646231216, "max": 350375.836157611, "count": 486 }, "SoccerTwos.Step.mean": { "value": 5039974.0, "min": 9490.0, "max": 5039974.0, "count": 504 }, "SoccerTwos.Step.sum": { "value": 5039974.0, "min": 9490.0, "max": 5039974.0, "count": 504 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.002235566731542349, "min": -0.09627772867679596, "max": 0.2157672941684723, "count": 504 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.4068731367588043, "min": -17.522546768188477, "max": 31.968029022216797, "count": 504 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0028875842690467834, "min": -0.09690847247838974, "max": 0.20935361087322235, "count": 504 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5255403518676758, "min": -17.63734245300293, "max": 32.936676025390625, "count": 504 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 504 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 504 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04841977881861257, "min": -0.7448999998159707, "max": 0.49603902930166666, "count": 504 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.812399744987488, "min": -53.0667998790741, "max": 62.418399810791016, "count": 504 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04841977881861257, "min": -0.7448999998159707, "max": 0.49603902930166666, "count": 504 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.812399744987488, "min": -53.0667998790741, "max": 62.418399810791016, "count": 504 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 504 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 504 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018131457284713784, "min": 0.0102237796279951, "max": 0.02380952551611699, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018131457284713784, "min": 0.0102237796279951, "max": 0.02380952551611699, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10317082603772482, "min": 2.910386441120257e-05, "max": 0.12334747438629469, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10317082603772482, "min": 2.910386441120257e-05, "max": 0.12334747438629469, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10539367496967315, "min": 4.007817624369636e-05, "max": 0.1256736213962237, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10539367496967315, "min": 4.007817624369636e-05, "max": 0.1256736213962237, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735672681", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/goksu/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1735687827" }, "total": 15145.157474238998, "count": 1, "self": 10.00505278199671, "children": { "run_training.setup": { "total": 0.010560717000089426, "count": 1, "self": 0.010560717000089426 }, "TrainerController.start_learning": { "total": 15135.141860740001, "count": 1, "self": 8.066763261431333, "children": { "TrainerController._reset_env": { "total": 2.6404170069940847, "count": 26, "self": 2.6404170069940847 }, "TrainerController.advance": { "total": 15124.063578526573, "count": 340424, "self": 8.442439406171616, "children": { "env_step": { "total": 11583.069352154791, "count": 340424, "self": 5185.497147794145, "children": { "SubprocessEnvManager._take_step": { "total": 6392.378750947274, "count": 340424, "self": 72.68926025633573, "children": { "TorchPolicy.evaluate": { "total": 6319.689490690938, "count": 640062, "self": 6319.689490690938 } } }, "workers": { "total": 5.1934534133715715, "count": 340423, "self": 0.0, "children": { "worker_root": { "total": 15115.388629628911, "count": 340423, "is_parallel": true, "self": 10920.306714321794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002012264000086361, "count": 2, "is_parallel": true, "self": 0.0005315159999099706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014807480001763906, "count": 8, "is_parallel": true, "self": 0.0014807480001763906 } } }, "UnityEnvironment.step": { "total": 0.01975647199992636, "count": 1, "is_parallel": true, "self": 0.0005029260000810609, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003927969999040215, "count": 1, "is_parallel": true, "self": 0.0003927969999040215 }, "communicator.exchange": { "total": 0.01712539300001481, "count": 1, "is_parallel": true, "self": 0.01712539300001481 }, "steps_from_proto": { "total": 0.001735355999926469, "count": 2, "is_parallel": true, "self": 0.00032445899978483794, "children": { "_process_rank_one_or_two_observation": { "total": 0.001410897000141631, "count": 8, "is_parallel": true, "self": 0.001410897000141631 } } } } } } }, "UnityEnvironment.step": { "total": 4195.03453491212, "count": 340422, "is_parallel": true, "self": 228.63141730686266, "children": { "UnityEnvironment._generate_step_input": { "total": 149.782167878172, "count": 340422, "is_parallel": true, "self": 149.782167878172 }, "communicator.exchange": { "total": 3156.5504728626443, "count": 340422, "is_parallel": true, "self": 3156.5504728626443 }, "steps_from_proto": { "total": 660.0704768644409, "count": 680844, "is_parallel": true, "self": 132.37095699071529, "children": { "_process_rank_one_or_two_observation": { "total": 527.6995198737256, "count": 2723376, "is_parallel": true, "self": 527.6995198737256 } } } } }, "steps_from_proto": { "total": 0.04738039499761726, "count": 50, "is_parallel": true, "self": 0.009436839973659517, "children": { "_process_rank_one_or_two_observation": { "total": 0.03794355502395774, "count": 200, "is_parallel": true, "self": 0.03794355502395774 } } } } } } } } }, "trainer_advance": { "total": 3532.5517869656105, "count": 340423, "self": 64.75684975253762, "children": { "process_trajectory": { "total": 1957.2375001620678, "count": 340423, "self": 1952.6583104280696, "children": { "RLTrainer._checkpoint": { "total": 4.5791897339981915, "count": 10, "self": 4.5791897339981915 } } }, "_update_policy": { "total": 1510.557437051005, "count": 241, "self": 695.7031842251074, "children": { "TorchPOCAOptimizer.update": { "total": 814.8542528258977, "count": 7230, "self": 814.8542528258977 } } } } } } }, "trainer_threads": { "total": 6.199989002197981e-07, "count": 1, "self": 6.199989002197981e-07 }, "TrainerController._save_models": { "total": 0.3711013250031101, "count": 1, "self": 4.095999975106679e-05, "children": { "RLTrainer._checkpoint": { "total": 0.37106036500335904, "count": 1, "self": 0.37106036500335904 } } } } } } }