{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.897956371307373, "min": 1.897956371307373, "max": 3.2957069873809814, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45672.421875, "min": 15056.080078125, "max": 111055.4921875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 442.3636363636364, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16484.0, "max": 26132.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1181.7998220046622, "min": 1180.786960974288, "max": 1199.4207269131573, "count": 121 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2363.5996440093245, "min": 2361.573921948576, "max": 16738.762614794054, "count": 121 }, "SoccerTwos.Step.mean": { "value": 4999522.0, "min": 9082.0, "max": 4999522.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999522.0, "min": 9082.0, "max": 4999522.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 2.997626143041998e-05, "min": -0.08423199504613876, "max": 0.09491100162267685, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0002997626143041998, "min": -0.8648865818977356, "max": 1.272194504737854, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 3.87626641895622e-05, "min": -0.10975539684295654, "max": 0.09483882039785385, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.000387626641895622, "min": -1.0975539684295654, "max": 1.306225061416626, "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": 0.0, "min": -0.5591692328453064, "max": 0.2917600005865097, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.891600012779236, "max": 4.376400008797646, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5591692328453064, "max": 0.2917600005865097, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.891600012779236, "max": 4.376400008797646, "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": 0.01742762657328664, "min": 0.011112835831348396, "max": 0.022888927767053247, "count": 229 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01742762657328664, "min": 0.011112835831348396, "max": 0.022888927767053247, "count": 229 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 7.469201908823682e-09, "min": 2.90180472983792e-09, "max": 0.012253172985704925, "count": 229 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 7.469201908823682e-09, "min": 2.90180472983792e-09, "max": 0.012253172985704925, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.5322401540155774e-08, "min": 7.1896608518547586e-09, "max": 0.006459781775871912, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.5322401540155774e-08, "min": 7.1896608518547586e-09, "max": 0.006459781775871912, "count": 229 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 229 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 229 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721424011", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/evgenii/anaconda3/envs/hf_ai_vs_ai/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=soccer_twos_basic_params --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721429399" }, "total": 5387.793256162, "count": 1, "self": 0.21909823100031645, "children": { "run_training.setup": { "total": 0.011307577000025049, "count": 1, "self": 0.011307577000025049 }, "TrainerController.start_learning": { "total": 5387.562850354, "count": 1, "self": 4.502430648020891, "children": { "TrainerController._reset_env": { "total": 2.8785338079994744, "count": 25, "self": 2.8785338079994744 }, "TrainerController.advance": { "total": 5379.98944362898, "count": 324401, "self": 4.212884191760168, "children": { "env_step": { "total": 4177.181727042024, "count": 324401, "self": 2938.2833763098342, "children": { "SubprocessEnvManager._take_step": { "total": 1236.2409861891056, "count": 324401, "self": 28.466274757111933, "children": { "TorchPolicy.evaluate": { "total": 1207.7747114319936, "count": 644568, "self": 1207.7747114319936 } } }, "workers": { "total": 2.6573645430842703, "count": 324401, "self": 0.0, "children": { "worker_root": { "total": 5381.82670776112, "count": 324401, "is_parallel": true, "self": 2992.172604458153, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018104759999744147, "count": 2, "is_parallel": true, "self": 0.0005467709999322778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012637050000421368, "count": 8, "is_parallel": true, "self": 0.0012637050000421368 } } }, "UnityEnvironment.step": { "total": 0.01722774800001048, "count": 1, "is_parallel": true, "self": 0.00037726199997223375, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003011020000087683, "count": 1, "is_parallel": true, "self": 0.0003011020000087683 }, "communicator.exchange": { "total": 0.015354194000025245, "count": 1, "is_parallel": true, "self": 0.015354194000025245 }, "steps_from_proto": { "total": 0.0011951900000042315, "count": 2, "is_parallel": true, "self": 0.0002418459999660172, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009533440000382143, "count": 8, "is_parallel": true, "self": 0.0009533440000382143 } } } } } } }, "UnityEnvironment.step": { "total": 2389.6250237589657, "count": 324400, "is_parallel": true, "self": 125.28330025650848, "children": { "UnityEnvironment._generate_step_input": { "total": 89.37477725101326, "count": 324400, "is_parallel": true, "self": 89.37477725101326 }, "communicator.exchange": { "total": 1785.418480443851, "count": 324400, "is_parallel": true, "self": 1785.418480443851 }, "steps_from_proto": { "total": 389.54846580759283, "count": 648800, "is_parallel": true, "self": 75.22799380102413, "children": { "_process_rank_one_or_two_observation": { "total": 314.3204720065687, "count": 2595200, "is_parallel": true, "self": 314.3204720065687 } } } } }, "steps_from_proto": { "total": 0.029079544001660906, "count": 48, "is_parallel": true, "self": 0.005771209000499766, "children": { "_process_rank_one_or_two_observation": { "total": 0.02330833500116114, "count": 192, "is_parallel": true, "self": 0.02330833500116114 } } } } } } } } }, "trainer_advance": { "total": 1198.5948323951952, "count": 324401, "self": 38.15757732013367, "children": { "process_trajectory": { "total": 324.63177605606126, "count": 324401, "self": 322.6132117540615, "children": { "RLTrainer._checkpoint": { "total": 2.0185643019997315, "count": 10, "self": 2.0185643019997315 } } }, "_update_policy": { "total": 835.8054790190004, "count": 229, "self": 443.5721942590023, "children": { "TorchPOCAOptimizer.update": { "total": 392.23328475999807, "count": 6873, "self": 392.23328475999807 } } } } } } }, "trainer_threads": { "total": 5.330002750270069e-07, "count": 1, "self": 5.330002750270069e-07 }, "TrainerController._save_models": { "total": 0.19244173599963688, "count": 1, "self": 0.0009216989992637536, "children": { "RLTrainer._checkpoint": { "total": 0.19152003700037312, "count": 1, "self": 0.19152003700037312 } } } } } } }