{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.29271167516708374, "min": 0.27912601828575134, "max": 3.2958128452301025, "count": 15999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 11614.798828125, "min": 4629.82958984375, "max": 591558.875, "count": 15999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 36.792307692307695, "min": 29.23170731707317, "max": 551.0, "count": 15999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19132.0, "min": 15260.0, "max": 41060.0, "count": 15999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1639.9359347156194, "min": 1198.128538137423, "max": 1680.737096359153, "count": 15999 }, "SoccerTwos.Self-play.ELO.sum": { "value": 426383.343026061, "min": 2397.64453146509, "max": 500426.5231898225, "count": 15999 }, "SoccerTwos.Step.mean": { "value": 159999996.0, "min": 9568.0, "max": 159999996.0, "count": 16000 }, "SoccerTwos.Step.sum": { "value": 159999996.0, "min": 9568.0, "max": 159999996.0, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.020044520497322083, "min": -0.12824246287345886, "max": 0.22821052372455597, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.211575508117676, "min": -30.2033634185791, "max": 49.52168273925781, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02062523551285267, "min": -0.1285647302865982, "max": 0.22626857459545135, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.362561225891113, "min": -30.095096588134766, "max": 49.10028076171875, "count": 16000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09029230796373808, "min": -0.46440799951553347, "max": 0.5237547838169595, "count": 16000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 23.4760000705719, "min": -82.58560001850128, "max": 93.47840017080307, "count": 16000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09029230796373808, "min": -0.46440799951553347, "max": 0.5237547838169595, "count": 16000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 23.4760000705719, "min": -82.58560001850128, "max": 93.47840017080307, "count": 16000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012796422930356736, "min": 0.00885343154077418, "max": 0.028058637352660298, "count": 7774 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012796422930356736, "min": 0.00885343154077418, "max": 0.028058637352660298, "count": 7774 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07961924796303113, "min": 0.005778578342869878, "max": 0.0951485348244508, "count": 7774 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07961924796303113, "min": 0.005778578342869878, "max": 0.0951485348244508, "count": 7774 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0797942062218984, "min": 0.005859525905301173, "max": 0.09544695367415747, "count": 7774 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0797942062218984, "min": 0.005859525905301173, "max": 0.09544695367415747, "count": 7774 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 5.747498117483374e-09, "min": 5.747498117483374e-09, "max": 0.000299961435012855, "count": 7774 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 5.747498117483374e-09, "min": 5.747498117483374e-09, "max": 0.000299961435012855, "count": 7774 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 7774 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 7774 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0188061749999443e-05, "min": 1.0188061749999443e-05, "max": 0.009998715785499998, "count": 7774 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0188061749999443e-05, "min": 1.0188061749999443e-05, "max": 0.009998715785499998, "count": 7774 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693767407", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/mgmeskill/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=Downstrike-160M --no-graphics --num-envs=8", "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": "1693901136" }, "total": 133728.72782940418, "count": 1, "self": 0.3201414127834141, "children": { "run_training.setup": { "total": 0.027171769179403782, "count": 1, "self": 0.027171769179403782 }, "TrainerController.start_learning": { "total": 133728.3805162222, "count": 1, "self": 102.86563353613019, "children": { "TrainerController._reset_env": { "total": 696.0709477802739, "count": 7947, "self": 696.0709477802739 }, "TrainerController.advance": { "total": 132929.13862727955, "count": 3507132, "self": 80.21517739770934, "children": { "env_step": { "total": 73052.17698274832, "count": 3507132, "self": 24081.407350266818, "children": { "SubprocessEnvManager._take_step": { "total": 48880.748980567325, "count": 14812115, "self": 1211.079614217393, "children": { "TorchPolicy.evaluate": { "total": 47669.66936634993, "count": 27112404, "self": 47669.66936634993 } } }, "workers": { "total": 90.02065191417933, "count": 3507132, "self": 0.0, "children": { "worker_root": { "total": 1066995.6906433739, "count": 14784608, "is_parallel": true, "self": 875481.2676103334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01907126046717167, "count": 16, "is_parallel": true, "self": 0.004095900803804398, "children": { "_process_rank_one_or_two_observation": { "total": 0.014975359663367271, "count": 64, "is_parallel": true, "self": 0.014975359663367271 } } }, "UnityEnvironment.step": { "total": 0.17750767897814512, "count": 8, "is_parallel": true, "self": 0.006570951547473669, "children": { "UnityEnvironment._generate_step_input": { "total": 0.004816613160073757, "count": 8, "is_parallel": true, "self": 0.004816613160073757 }, "communicator.exchange": { "total": 0.14813531283289194, "count": 8, "is_parallel": true, "self": 0.14813531283289194 }, "steps_from_proto": { "total": 0.017984801437705755, "count": 16, "is_parallel": true, "self": 0.0031336508691310883, "children": { "_process_rank_one_or_two_observation": { "total": 0.014851150568574667, "count": 64, "is_parallel": true, "self": 0.014851150568574667 } } } } } } }, "UnityEnvironment.step": { "total": 191352.52964038588, "count": 14784600, "is_parallel": true, "self": 12493.37244902039, "children": { "UnityEnvironment._generate_step_input": { "total": 8003.242103095632, "count": 14784600, "is_parallel": true, "self": 8003.242103095632 }, "communicator.exchange": { "total": 137369.81809696788, "count": 14784600, "is_parallel": true, "self": 137369.81809696788 }, "steps_from_proto": { "total": 33486.09699130198, "count": 29569200, "is_parallel": true, "self": 5620.8086648634635, "children": { "_process_rank_one_or_two_observation": { "total": 27865.288326438516, "count": 118276800, "is_parallel": true, "self": 27865.288326438516 } } } } }, "steps_from_proto": { "total": 161.89339265460148, "count": 127136, "is_parallel": true, "self": 25.868383669760078, "children": { "_process_rank_one_or_two_observation": { "total": 136.0250089848414, "count": 508544, "is_parallel": true, "self": 136.0250089848414 } } } } } } } } }, "trainer_advance": { "total": 59796.74646713352, "count": 3507132, "self": 1285.6652827882208, "children": { "process_trajectory": { "total": 24676.622614394873, "count": 3507132, "self": 24650.985279567074, "children": { "RLTrainer._checkpoint": { "total": 25.63733482779935, "count": 80, "self": 25.63733482779935 } } }, "_update_policy": { "total": 33834.458569950424, "count": 7774, "self": 18988.026603292674, "children": { "TorchPOCAOptimizer.update": { "total": 14846.43196665775, "count": 233220, "self": 14846.43196665775 } } } } } } }, "trainer_threads": { "total": 5.522742867469788e-07, "count": 1, "self": 5.522742867469788e-07 }, "TrainerController._save_models": { "total": 0.30530707398429513, "count": 1, "self": 0.0019307197071611881, "children": { "RLTrainer._checkpoint": { "total": 0.30337635427713394, "count": 1, "self": 0.30337635427713394 } } } } } } }