{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9117426872253418, "min": 1.8935515880584717, "max": 3.2958154678344727, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34197.25390625, "min": 11284.8720703125, "max": 156884.59375, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 91.03703703703704, "min": 58.855421686746986, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19664.0, "min": 14736.0, "max": 26944.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1549.3105247203912, "min": 1198.995732238514, "max": 1554.0632496988235, "count": 991 }, "SoccerTwos.Self-play.ELO.sum": { "value": 167325.53666980224, "min": 2399.988650352016, "max": 252261.06419093508, "count": 991 }, "SoccerTwos.Step.mean": { "value": 9999930.0, "min": 9488.0, "max": 9999930.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999930.0, "min": 9488.0, "max": 9999930.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03622465953230858, "min": -0.06369412690401077, "max": 0.29628443717956543, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.9122631549835205, "min": -7.834377288818359, "max": 34.665279388427734, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.031150951981544495, "min": -0.06783859431743622, "max": 0.2975817024707794, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.36430287361145, "min": -8.344146728515625, "max": 34.81705856323242, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.047122221853997975, "min": -0.6654666662216187, "max": 0.7164051257647001, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.089199960231781, "min": -43.11479997634888, "max": 83.81939971446991, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.047122221853997975, "min": -0.6654666662216187, "max": 0.7164051257647001, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.089199960231781, "min": -43.11479997634888, "max": 83.81939971446991, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.044444552089362335, "min": 0.024826668005736793, "max": 0.044444552089362335, "count": 48 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.044444552089362335, "min": 0.024826668005736793, "max": 0.044444552089362335, "count": 48 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.041815283140167595, "min": 0.0017440978766826447, "max": 0.046863706219941376, "count": 48 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.041815283140167595, "min": 0.0017440978766826447, "max": 0.046863706219941376, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.05082895865291357, "min": 0.0020050259048293812, "max": 0.056569876328110696, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.05082895865291357, "min": 0.0020050259048293812, "max": 0.056569876328110696, "count": 48 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00020000000000000006, "min": 0.00020000000000000006, "max": 0.00020000000000000006, "count": 48 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00020000000000000006, "min": 0.00020000000000000006, "max": 0.00020000000000000006, "count": 48 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 48 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 48 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 48 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735825865", "python_version": "3.10.12 (main, Dec 30 2024, 13:56:33) [GCC 13.2.0]", "command_line_arguments": "/home/arbocensus/HUggin course/UNIT 1/Pythondef/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1735841816" }, "total": 15951.473110803, "count": 1, "self": 0.5528875389973109, "children": { "run_training.setup": { "total": 0.013804518000142707, "count": 1, "self": 0.013804518000142707 }, "TrainerController.start_learning": { "total": 15950.906418746, "count": 1, "self": 11.139694862784381, "children": { "TrainerController._reset_env": { "total": 3.354530151003928, "count": 50, "self": 3.354530151003928 }, "TrainerController.advance": { "total": 15935.947894063207, "count": 663473, "self": 12.159737516099995, "children": { "env_step": { "total": 8683.528597746636, "count": 663473, "self": 6037.034235776266, "children": { "SubprocessEnvManager._take_step": { "total": 2639.2826521802963, "count": 663473, "self": 62.55167177670137, "children": { "TorchPolicy.evaluate": { "total": 2576.730980403595, "count": 1266182, "self": 2576.730980403595 } } }, "workers": { "total": 7.211709790073201, "count": 663473, "self": 0.0, "children": { "worker_root": { "total": 15937.01295609342, "count": 663473, "is_parallel": true, "self": 11177.626629156597, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021623459997499594, "count": 2, "is_parallel": true, "self": 0.0009755060000316007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011868399997183587, "count": 8, "is_parallel": true, "self": 0.0011868399997183587 } } }, "UnityEnvironment.step": { "total": 0.021429484000236698, "count": 1, "is_parallel": true, "self": 0.00036936100013917894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035990200012747664, "count": 1, "is_parallel": true, "self": 0.00035990200012747664 }, "communicator.exchange": { "total": 0.01962817699995867, "count": 1, "is_parallel": true, "self": 0.01962817699995867 }, "steps_from_proto": { "total": 0.001072044000011374, "count": 2, "is_parallel": true, "self": 0.00022705399987899, "children": { "_process_rank_one_or_two_observation": { "total": 0.000844990000132384, "count": 8, "is_parallel": true, "self": 0.000844990000132384 } } } } } } }, "UnityEnvironment.step": { "total": 4759.33198895784, "count": 663472, "is_parallel": true, "self": 229.93075190823765, "children": { "UnityEnvironment._generate_step_input": { "total": 166.73766909036294, "count": 663472, "is_parallel": true, "self": 166.73766909036294 }, "communicator.exchange": { "total": 3663.1833402992015, "count": 663472, "is_parallel": true, "self": 3663.1833402992015 }, "steps_from_proto": { "total": 699.480227660038, "count": 1326944, "is_parallel": true, "self": 139.36203788906596, "children": { "_process_rank_one_or_two_observation": { "total": 560.1181897709721, "count": 5307776, "is_parallel": true, "self": 560.1181897709721 } } } } }, "steps_from_proto": { "total": 0.05433797898285775, "count": 98, "is_parallel": true, "self": 0.01087898699051948, "children": { "_process_rank_one_or_two_observation": { "total": 0.04345899199233827, "count": 392, "is_parallel": true, "self": 0.04345899199233827 } } } } } } } } }, "trainer_advance": { "total": 7240.2595588004715, "count": 663473, "self": 89.71311573571256, "children": { "process_trajectory": { "total": 1193.2849399947618, "count": 663473, "self": 1181.6466693017596, "children": { "RLTrainer._checkpoint": { "total": 11.638270693002141, "count": 20, "self": 11.638270693002141 } } }, "_update_policy": { "total": 5957.261503069997, "count": 48, "self": 1685.5382900818577, "children": { "TorchPOCAOptimizer.update": { "total": 4271.7232129881395, "count": 48030, "self": 4271.7232129881395 } } } } } } }, "trainer_threads": { "total": 5.790025170426816e-07, "count": 1, "self": 5.790025170426816e-07 }, "TrainerController._save_models": { "total": 0.46429909000289626, "count": 1, "self": 0.006499684001028072, "children": { "RLTrainer._checkpoint": { "total": 0.4577994060018682, "count": 1, "self": 0.4577994060018682 } } } } } } }