{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.869733452796936, "min": 1.8288425207138062, "max": 3.295680284500122, "count": 755 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38351.97265625, "min": 16491.24609375, "max": 127750.984375, "count": 755 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.093023255813954, "min": 41.62931034482759, "max": 999.0, "count": 755 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19296.0, "min": 14640.0, "max": 25392.0, "count": 755 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1469.522847192251, "min": 1185.2975081231273, "max": 1515.4705660695133, "count": 731 }, "SoccerTwos.Self-play.ELO.sum": { "value": 252757.92971706716, "min": 2370.5950162462545, "max": 333977.8624059555, "count": 731 }, "SoccerTwos.Step.mean": { "value": 7549984.0, "min": 9990.0, "max": 7549984.0, "count": 755 }, "SoccerTwos.Step.sum": { "value": 7549984.0, "min": 9990.0, "max": 7549984.0, "count": 755 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.044055331498384476, "min": -0.15102851390838623, "max": 0.1658662110567093, "count": 755 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.577517032623291, "min": -28.242332458496094, "max": 22.6661376953125, "count": 755 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04948036000132561, "min": -0.15268553793430328, "max": 0.16741126775741577, "count": 755 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.510622024536133, "min": -28.552194595336914, "max": 22.265403747558594, "count": 755 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 755 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 755 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.053179069313892095, "min": -0.6865904785337902, "max": 0.4144500017166138, "count": 755 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.146799921989441, "min": -58.91720008850098, "max": 49.9891996383667, "count": 755 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.053179069313892095, "min": -0.6865904785337902, "max": 0.4144500017166138, "count": 755 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.146799921989441, "min": -58.91720008850098, "max": 49.9891996383667, "count": 755 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 755 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 755 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013682717209060986, "min": 0.01074417207079629, "max": 0.02316420157828058, "count": 363 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013682717209060986, "min": 0.01074417207079629, "max": 0.02316420157828058, "count": 363 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1181153250237306, "min": 3.1416401043316e-06, "max": 0.12238245805104574, "count": 363 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1181153250237306, "min": 3.1416401043316e-06, "max": 0.12238245805104574, "count": 363 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12016588772336642, "min": 1.2618198570635287e-05, "max": 0.1245737537741661, "count": 363 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12016588772336642, "min": 1.2618198570635287e-05, "max": 0.1245737537741661, "count": 363 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 363 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 363 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 363 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 363 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 363 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 363 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676138001", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/css/anaconda3/envs/rl_course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "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": "1676180193" }, "total": 42191.540514424996, "count": 1, "self": 0.0036059089907212183, "children": { "run_training.setup": { "total": 0.13660803800030408, "count": 1, "self": 0.13660803800030408 }, "TrainerController.start_learning": { "total": 42191.400300478, "count": 1, "self": 7.256411541078705, "children": { "TrainerController._reset_env": { "total": 11.555317614986052, "count": 38, "self": 11.555317614986052 }, "TrainerController.advance": { "total": 42172.302790482936, "count": 516667, "self": 6.64878363115713, "children": { "env_step": { "total": 40113.46188635869, "count": 516667, "self": 38643.268364980606, "children": { "SubprocessEnvManager._take_step": { "total": 1465.7256713260076, "count": 516667, "self": 38.07819719355757, "children": { "TorchPolicy.evaluate": { "total": 1427.64747413245, "count": 953520, "self": 1427.64747413245 } } }, "workers": { "total": 4.467850052074937, "count": 516666, "self": 0.0, "children": { "worker_root": { "total": 42180.143281419565, "count": 516666, "is_parallel": true, "self": 4400.139482353479, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020667460003096494, "count": 2, "is_parallel": true, "self": 0.00036049200025445316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017062540000551962, "count": 8, "is_parallel": true, "self": 0.0017062540000551962 } } }, "UnityEnvironment.step": { "total": 0.13621059900015098, "count": 1, "is_parallel": true, "self": 0.00016826499995659105, "children": { "UnityEnvironment._generate_step_input": { "total": 0.002248804999908316, "count": 1, "is_parallel": true, "self": 0.002248804999908316 }, "communicator.exchange": { "total": 0.13196066500040615, "count": 1, "is_parallel": true, "self": 0.13196066500040615 }, "steps_from_proto": { "total": 0.001832863999879919, "count": 2, "is_parallel": true, "self": 0.00026673299998947186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015661309998904471, "count": 8, "is_parallel": true, "self": 0.0015661309998904471 } } } } } } }, "UnityEnvironment.step": { "total": 37779.93516791707, "count": 516665, "is_parallel": true, "self": 73.66751974359795, "children": { "UnityEnvironment._generate_step_input": { "total": 658.355059391859, "count": 516665, "is_parallel": true, "self": 658.355059391859 }, "communicator.exchange": { "total": 36129.33761935332, "count": 516665, "is_parallel": true, "self": 36129.33761935332 }, "steps_from_proto": { "total": 918.5749694282913, "count": 1033330, "is_parallel": true, "self": 123.89298991918076, "children": { "_process_rank_one_or_two_observation": { "total": 794.6819795091105, "count": 4133320, "is_parallel": true, "self": 794.6819795091105 } } } } }, "steps_from_proto": { "total": 0.06863114901443623, "count": 74, "is_parallel": true, "self": 0.009315816037997138, "children": { "_process_rank_one_or_two_observation": { "total": 0.059315332976439095, "count": 296, "is_parallel": true, "self": 0.059315332976439095 } } } } } } } } }, "trainer_advance": { "total": 2052.1921204930877, "count": 516666, "self": 56.59559264291693, "children": { "process_trajectory": { "total": 793.5043975362314, "count": 516666, "self": 789.4839403192309, "children": { "RLTrainer._checkpoint": { "total": 4.020457217000512, "count": 15, "self": 4.020457217000512 } } }, "_update_policy": { "total": 1202.0921303139394, "count": 364, "self": 863.772296696925, "children": { "TorchPOCAOptimizer.update": { "total": 338.3198336170144, "count": 10920, "self": 338.3198336170144 } } } } } } }, "trainer_threads": { "total": 6.010013748891652e-07, "count": 1, "self": 6.010013748891652e-07 }, "TrainerController._save_models": { "total": 0.28578023800218944, "count": 1, "self": 0.0008242700059781782, "children": { "RLTrainer._checkpoint": { "total": 0.28495596799621126, "count": 1, "self": 0.28495596799621126 } } } } } } }