{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5601428747177124, "min": 1.4417721033096313, "max": 3.295738458633423, "count": 2709 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28806.478515625, "min": 24832.6015625, "max": 126014.109375, "count": 2709 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.92647058823529, "min": 42.575221238938056, "max": 999.0, "count": 2709 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19836.0, "min": 12828.0, "max": 29272.0, "count": 2709 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1563.4670442130682, "min": 1188.3596090064598, "max": 1714.2486869050654, "count": 2656 }, "SoccerTwos.Self-play.ELO.sum": { "value": 212631.51801297726, "min": 2377.8427529048986, "max": 379893.464240887, "count": 2656 }, "SoccerTwos.Step.mean": { "value": 27089965.0, "min": 9658.0, "max": 27089965.0, "count": 2709 }, "SoccerTwos.Step.sum": { "value": 27089965.0, "min": 9658.0, "max": 27089965.0, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.009520798921585083, "min": -0.14038220047950745, "max": 0.19671949744224548, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.2948286533355713, "min": -27.99988555908203, "max": 35.47391128540039, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01134029496461153, "min": -0.1391388475894928, "max": 0.19458019733428955, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.5422800779342651, "min": -28.105087280273438, "max": 35.61205291748047, "count": 2709 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2709 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07649117752033122, "min": -0.5555555555555556, "max": 0.5913942864962987, "count": 2709 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -10.402800142765045, "min": -65.84240025281906, "max": 63.599599719047546, "count": 2709 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07649117752033122, "min": -0.5555555555555556, "max": 0.5913942864962987, "count": 2709 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -10.402800142765045, "min": -65.84240025281906, "max": 63.599599719047546, "count": 2709 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2709 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2709 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020541020669043064, "min": 0.010876827927616736, "max": 0.025076277546274166, "count": 1310 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020541020669043064, "min": 0.010876827927616736, "max": 0.025076277546274166, "count": 1310 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08825714389483134, "min": 1.5450951404242612e-07, "max": 0.12343068520228068, "count": 1310 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08825714389483134, "min": 1.5450951404242612e-07, "max": 0.12343068520228068, "count": 1310 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08932124450802803, "min": 1.6743716197235395e-07, "max": 0.12648289601008098, "count": 1310 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08932124450802803, "min": 1.6743716197235395e-07, "max": 0.12648289601008098, "count": 1310 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1310 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1310 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1310 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1310 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1310 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1310 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687280374", "python_version": "3.9.16 (main, May 15 2023, 18:51:40) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "1687431800" }, "total": 118181.298536375, "count": 1, "self": 1.2689139169960981, "children": { "run_training.setup": { "total": 0.16632549999999924, "count": 1, "self": 0.16632549999999924 }, "TrainerController.start_learning": { "total": 118179.863296958, "count": 1, "self": 25.65550733031705, "children": { "TrainerController._reset_env": { "total": 8.996221005999512, "count": 136, "self": 8.996221005999512 }, "TrainerController.advance": { "total": 118144.99357449668, "count": 1857146, "self": 24.844171567980084, "children": { "env_step": { "total": 24541.27971706602, "count": 1857146, "self": 19811.31751008785, "children": { "SubprocessEnvManager._take_step": { "total": 4714.064907265323, "count": 1857146, "self": 117.80869498255743, "children": { "TorchPolicy.evaluate": { "total": 4596.256212282766, "count": 3410898, "self": 4596.256212282766 } } }, "workers": { "total": 15.897299712844864, "count": 1857146, "self": 0.0, "children": { "worker_root": { "total": 118130.20011573363, "count": 1857146, "is_parallel": true, "self": 101206.66483704708, "children": { "steps_from_proto": { "total": 0.2146107889924247, "count": 272, "is_parallel": true, "self": 0.03253864796589934, "children": { "_process_rank_one_or_two_observation": { "total": 0.18207214102652536, "count": 1088, "is_parallel": true, "self": 0.18207214102652536 } } }, "UnityEnvironment.step": { "total": 16923.320667897555, "count": 1857146, "is_parallel": true, "self": 743.6909920914295, "children": { "UnityEnvironment._generate_step_input": { "total": 465.1265789668495, "count": 1857146, "is_parallel": true, "self": 465.1265789668495 }, "communicator.exchange": { "total": 13385.88423795382, "count": 1857146, "is_parallel": true, "self": 13385.88423795382 }, "steps_from_proto": { "total": 2328.6188588854575, "count": 3714292, "is_parallel": true, "self": 395.06696780542006, "children": { "_process_rank_one_or_two_observation": { "total": 1933.5518910800374, "count": 14857168, "is_parallel": true, "self": 1933.5518910800374 } } } } } } } } } } }, "trainer_advance": { "total": 93578.86968586268, "count": 1857146, "self": 229.2591687321401, "children": { "process_trajectory": { "total": 11709.479198741694, "count": 1857146, "self": 11697.249915698718, "children": { "RLTrainer._checkpoint": { "total": 12.229283042976022, "count": 54, "self": 12.229283042976022 } } }, "_update_policy": { "total": 81640.13131838884, "count": 1311, "self": 3230.999867635168, "children": { "TorchPOCAOptimizer.update": { "total": 78409.13145075367, "count": 39304, "self": 78409.13145075367 } } } } } } }, "trainer_threads": { "total": 1.1250085663050413e-06, "count": 1, "self": 1.1250085663050413e-06 }, "TrainerController._save_models": { "total": 0.21799299999838695, "count": 1, "self": 0.005156874991371296, "children": { "RLTrainer._checkpoint": { "total": 0.21283612500701565, "count": 1, "self": 0.21283612500701565 } } } } } } }