{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.88508939743042, "min": 0.32007288932800293, "max": 3.295736312866211, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38365.33984375, "min": 3157.25439453125, "max": 135342.46875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 93.16981132075472, "min": 66.58333333333333, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19752.0, "min": 14780.0, "max": 25008.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1512.427935707163, "min": 1170.3451905441245, "max": 1525.702528180523, "count": 1457 }, "SoccerTwos.Self-play.ELO.sum": { "value": 160317.36118495927, "min": 2340.9549261537477, "max": 226001.99945326115, "count": 1457 }, "SoccerTwos.Step.mean": { "value": 49999888.0, "min": 9520.0, "max": 49999888.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999888.0, "min": 9520.0, "max": 49999888.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.021812312304973602, "min": -0.13352897763252258, "max": 0.08573879301548004, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.312105178833008, "min": -13.512857437133789, "max": 8.831095695495605, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.020299047231674194, "min": -0.1314021795988083, "max": 0.0843314379453659, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.1516990661621094, "min": -13.528635025024414, "max": 8.686138153076172, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14448867991285505, "min": -0.7333333333333333, "max": 0.4688516100568156, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.315800070762634, "min": -45.10600012540817, "max": 41.33040010929108, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14448867991285505, "min": -0.7333333333333333, "max": 0.4688516100568156, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.315800070762634, "min": -45.10600012540817, "max": 41.33040010929108, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01772666120547607, "min": 0.010309555162287628, "max": 0.02550357847746151, "count": 2317 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01772666120547607, "min": 0.010309555162287628, "max": 0.02550357847746151, "count": 2317 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07129886721571287, "min": 1.7289252079334452e-13, "max": 0.08477772573630014, "count": 2317 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07129886721571287, "min": 1.7289252079334452e-13, "max": 0.08477772573630014, "count": 2317 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07237084607283274, "min": 1.806328044271103e-13, "max": 0.0861017644405365, "count": 2317 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07237084607283274, "min": 1.806328044271103e-13, "max": 0.0861017644405365, "count": 2317 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2317 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2317 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2317 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2317 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2317 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2317 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691503209", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/shubham/anaconda3/envs/rl_7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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", "numpy_version": "1.21.2", "end_time_seconds": "1691594759" }, "total": 91550.12136934884, "count": 1, "self": 0.21866557747125626, "children": { "run_training.setup": { "total": 0.007789118215441704, "count": 1, "self": 0.007789118215441704 }, "TrainerController.start_learning": { "total": 91549.89491465315, "count": 1, "self": 34.558459451422095, "children": { "TrainerController._reset_env": { "total": 15.585894523188472, "count": 249, "self": 15.585894523188472 }, "TrainerController.advance": { "total": 91499.61708582379, "count": 3267196, "self": 32.871663462370634, "children": { "env_step": { "total": 50005.42744296044, "count": 3267196, "self": 44438.527459194884, "children": { "SubprocessEnvManager._take_step": { "total": 5545.596074255183, "count": 3267196, "self": 237.7563860118389, "children": { "TorchPolicy.evaluate": { "total": 5307.839688243344, "count": 6432068, "self": 5307.839688243344 } } }, "workers": { "total": 21.30390951037407, "count": 3267196, "self": 0.0, "children": { "worker_root": { "total": 91468.98101312853, "count": 3267196, "is_parallel": true, "self": 52545.723739005625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003239186480641365, "count": 2, "is_parallel": true, "self": 0.0005889143794775009, "children": { "_process_rank_one_or_two_observation": { "total": 0.002650272101163864, "count": 8, "is_parallel": true, "self": 0.002650272101163864 } } }, "UnityEnvironment.step": { "total": 0.022952860221266747, "count": 1, "is_parallel": true, "self": 0.0008996389806270599, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006436463445425034, "count": 1, "is_parallel": true, "self": 0.0006436463445425034 }, "communicator.exchange": { "total": 0.01872406341135502, "count": 1, "is_parallel": true, "self": 0.01872406341135502 }, "steps_from_proto": { "total": 0.0026855114847421646, "count": 2, "is_parallel": true, "self": 0.00039279647171497345, "children": { "_process_rank_one_or_two_observation": { "total": 0.002292715013027191, "count": 8, "is_parallel": true, "self": 0.002292715013027191 } } } } } } }, "UnityEnvironment.step": { "total": 38922.63351684064, "count": 3267195, "is_parallel": true, "self": 2651.4995847065, "children": { "UnityEnvironment._generate_step_input": { "total": 1685.1483978647739, "count": 3267195, "is_parallel": true, "self": 1685.1483978647739 }, "communicator.exchange": { "total": 26989.567140348256, "count": 3267195, "is_parallel": true, "self": 26989.567140348256 }, "steps_from_proto": { "total": 7596.418393921107, "count": 6534390, "is_parallel": true, "self": 1098.265936370939, "children": { "_process_rank_one_or_two_observation": { "total": 6498.152457550168, "count": 26137560, "is_parallel": true, "self": 6498.152457550168 } } } } }, "steps_from_proto": { "total": 0.6237572822719812, "count": 496, "is_parallel": true, "self": 0.0929538756608963, "children": { "_process_rank_one_or_two_observation": { "total": 0.5308034066110849, "count": 1984, "is_parallel": true, "self": 0.5308034066110849 } } } } } } } } }, "trainer_advance": { "total": 41461.31797940098, "count": 3267196, "self": 387.35703905671835, "children": { "process_trajectory": { "total": 5851.3373470995575, "count": 3267196, "self": 5838.157907405868, "children": { "RLTrainer._checkpoint": { "total": 13.179439693689346, "count": 100, "self": 13.179439693689346 } } }, "_update_policy": { "total": 35222.6235932447, "count": 2317, "self": 5723.476034210995, "children": { "TorchPOCAOptimizer.update": { "total": 29499.147559033707, "count": 69510, "self": 29499.147559033707 } } } } } } }, "trainer_threads": { "total": 5.699694156646729e-07, "count": 1, "self": 5.699694156646729e-07 }, "TrainerController._save_models": { "total": 0.13347428478300571, "count": 1, "self": 0.0008611921221017838, "children": { "RLTrainer._checkpoint": { "total": 0.13261309266090393, "count": 1, "self": 0.13261309266090393 } } } } } } }