{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7277859449386597, "min": 1.5845156908035278, "max": 3.2957093715667725, "count": 925 }, "SoccerTwos.Policy.Entropy.sum": { "value": 51971.80078125, "min": 10495.83203125, "max": 118276.1328125, "count": 925 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 406.25, "max": 999.0, "count": 925 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 10208.0, "max": 31256.0, "count": 925 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1167.987453557424, "min": 1167.987453557424, "max": 1203.458984891552, "count": 176 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2335.974907114848, "min": 2335.974907114848, "max": 16554.059327683713, "count": 176 }, "SoccerTwos.Step.mean": { "value": 9249336.0, "min": 9644.0, "max": 9249336.0, "count": 925 }, "SoccerTwos.Step.sum": { "value": 9249336.0, "min": 9644.0, "max": 9249336.0, "count": 925 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -4.360767434263835e-06, "min": -0.02290487475693226, "max": 0.018366185948252678, "count": 925 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.3607673433143646e-05, "min": -0.4671410322189331, "max": 0.2366866171360016, "count": 925 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 6.418959230813925e-08, "min": -0.022667037323117256, "max": 0.017096394672989845, "count": 925 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.418958946596831e-07, "min": -0.47761547565460205, "max": 0.2906387150287628, "count": 925 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 925 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 925 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5, "max": 0.19183332721392313, "count": 925 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.196799993515015, "max": 2.625599980354309, "count": 925 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5, "max": 0.19183332721392313, "count": 925 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.196799993515015, "max": 2.625599980354309, "count": 925 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 925 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 925 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01548712404910475, "min": 0.010901510767871514, "max": 0.024092827644199132, "count": 421 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01548712404910475, "min": 0.010901510767871514, "max": 0.024092827644199132, "count": 421 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.2115560632807175e-10, "min": 1.2525940678205966e-10, "max": 0.005270237568765879, "count": 421 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.2115560632807175e-10, "min": 1.2525940678205966e-10, "max": 0.005270237568765879, "count": 421 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.4895151218284894e-10, "min": 2.161151863947867e-10, "max": 0.00562766349563996, "count": 421 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.4895151218284894e-10, "min": 2.161151863947867e-10, "max": 0.00562766349563996, "count": 421 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 421 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 421 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 421 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 421 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 421 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 421 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696910457", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/andre/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1696938709" }, "total": 28251.283201412996, "count": 1, "self": 0.7387690069153905, "children": { "run_training.setup": { "total": 0.025433712056837976, "count": 1, "self": 0.025433712056837976 }, "TrainerController.start_learning": { "total": 28250.518998694024, "count": 1, "self": 13.822300372412428, "children": { "TrainerController._reset_env": { "total": 16.382302765967324, "count": 47, "self": 16.382302765967324 }, "TrainerController.advance": { "total": 28220.146860206616, "count": 603631, "self": 15.59569749282673, "children": { "env_step": { "total": 16125.309724065126, "count": 603631, "self": 14194.152780992445, "children": { "SubprocessEnvManager._take_step": { "total": 1921.4464951547561, "count": 603631, "self": 95.29192452703137, "children": { "TorchPolicy.evaluate": { "total": 1826.1545706277248, "count": 1200610, "self": 1826.1545706277248 } } }, "workers": { "total": 9.710447917925194, "count": 603631, "self": 0.0, "children": { "worker_root": { "total": 28195.35456183448, "count": 603631, "is_parallel": true, "self": 15623.800765804946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01977797702420503, "count": 2, "is_parallel": true, "self": 0.004825939889997244, "children": { "_process_rank_one_or_two_observation": { "total": 0.014952037134207785, "count": 8, "is_parallel": true, "self": 0.014952037134207785 } } }, "UnityEnvironment.step": { "total": 0.06265705497935414, "count": 1, "is_parallel": true, "self": 0.0010249390034005046, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010153739713132381, "count": 1, "is_parallel": true, "self": 0.0010153739713132381 }, "communicator.exchange": { "total": 0.052452530013397336, "count": 1, "is_parallel": true, "self": 0.052452530013397336 }, "steps_from_proto": { "total": 0.008164211991243064, "count": 2, "is_parallel": true, "self": 0.0005206428468227386, "children": { "_process_rank_one_or_two_observation": { "total": 0.007643569144420326, "count": 8, "is_parallel": true, "self": 0.007643569144420326 } } } } } } }, "UnityEnvironment.step": { "total": 12571.477361750323, "count": 603630, "is_parallel": true, "self": 355.32757983438205, "children": { "UnityEnvironment._generate_step_input": { "total": 251.32221179909538, "count": 603630, "is_parallel": true, "self": 251.32221179909538 }, "communicator.exchange": { "total": 10870.05512512708, "count": 603630, "is_parallel": true, "self": 10870.05512512708 }, "steps_from_proto": { "total": 1094.772444989765, "count": 1207260, "is_parallel": true, "self": 226.25903193443082, "children": { "_process_rank_one_or_two_observation": { "total": 868.5134130553342, "count": 4829040, "is_parallel": true, "self": 868.5134130553342 } } } } }, "steps_from_proto": { "total": 0.07643427920993418, "count": 92, "is_parallel": true, "self": 0.01602080126758665, "children": { "_process_rank_one_or_two_observation": { "total": 0.06041347794234753, "count": 368, "is_parallel": true, "self": 0.06041347794234753 } } } } } } } } }, "trainer_advance": { "total": 12079.241438648663, "count": 603631, "self": 109.91249120095745, "children": { "process_trajectory": { "total": 1393.8569600542542, "count": 603631, "self": 1390.869883102947, "children": { "RLTrainer._checkpoint": { "total": 2.9870769513072446, "count": 18, "self": 2.9870769513072446 } } }, "_update_policy": { "total": 10575.471987393452, "count": 422, "self": 1097.0364471984794, "children": { "TorchPOCAOptimizer.update": { "total": 9478.435540194972, "count": 12714, "self": 9478.435540194972 } } } } } } }, "trainer_threads": { "total": 1.3540266081690788e-06, "count": 1, "self": 1.3540266081690788e-06 }, "TrainerController._save_models": { "total": 0.16753399500157684, "count": 1, "self": 0.004396683070808649, "children": { "RLTrainer._checkpoint": { "total": 0.1631373119307682, "count": 1, "self": 0.1631373119307682 } } } } } } }