{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6376081705093384, "min": 1.6376081705093384, "max": 3.295656681060791, "count": 570 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33485.8125, "min": 21896.3046875, "max": 106644.78125, "count": 570 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 41.21848739495798, "min": 37.56923076923077, "max": 999.0, "count": 570 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19620.0, "min": 16264.0, "max": 25124.0, "count": 570 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1623.4118014485496, "min": 1196.13662078987, "max": 1633.231621633894, "count": 561 }, "SoccerTwos.Self-play.ELO.sum": { "value": 386372.00874475477, "min": 2393.552613964721, "max": 422733.370125633, "count": 561 }, "SoccerTwos.Step.mean": { "value": 5699984.0, "min": 9620.0, "max": 5699984.0, "count": 570 }, "SoccerTwos.Step.sum": { "value": 5699984.0, "min": 9620.0, "max": 5699984.0, "count": 570 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05387691780924797, "min": -0.1729194074869156, "max": 0.2150198072195053, "count": 568 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.93701457977295, "min": -38.56102752685547, "max": 33.75811004638672, "count": 568 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05515898019075394, "min": -0.17391036450862885, "max": 0.2114037424325943, "count": 568 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.197273254394531, "min": -38.782012939453125, "max": 33.19038772583008, "count": 568 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 570 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 570 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0127142850591355, "min": -0.6329066673914592, "max": 0.4801157932532461, "count": 570 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.0259998440742493, "min": -67.31239998340607, "max": 60.50960010290146, "count": 570 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0127142850591355, "min": -0.6329066673914592, "max": 0.4801157932532461, "count": 570 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.0259998440742493, "min": -67.31239998340607, "max": 60.50960010290146, "count": 570 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 570 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 570 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01641471466476408, "min": 0.009967657426993052, "max": 0.025575490109622477, "count": 274 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01641471466476408, "min": 0.009967657426993052, "max": 0.025575490109622477, "count": 274 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12257067436973254, "min": 0.0003040206989680883, "max": 0.13078598901629448, "count": 273 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12257067436973254, "min": 0.0003040206989680883, "max": 0.13078598901629448, "count": 273 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12506366968154908, "min": 0.000316399738464194, "max": 0.13448004946112632, "count": 273 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12506366968154908, "min": 0.000316399738464194, "max": 0.13448004946112632, "count": 273 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 274 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 274 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 274 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 274 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 274 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 274 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727987160", "python_version": "3.10.15 (main, Sep 7 2024, 00:20:06) [Clang 16.0.0 (clang-1600.0.26.3)]", "command_line_arguments": "/Users/agruzdev/.virtualenvs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../SoccerTwos/SoccerTwos.app --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": "2.4.1", "numpy_version": "1.23.5", "end_time_seconds": "1728007885" }, "total": 20724.929886374972, "count": 1, "self": 0.23222574894316494, "children": { "run_training.setup": { "total": 0.017382542020641267, "count": 1, "self": 0.017382542020641267 }, "TrainerController.start_learning": { "total": 20724.680278084008, "count": 1, "self": 4.427394074620679, "children": { "TrainerController._reset_env": { "total": 5.8810676268767565, "count": 29, "self": 5.8810676268767565 }, "TrainerController.advance": { "total": 20714.300506591564, "count": 392692, "self": 3.721601637545973, "children": { "env_step": { "total": 16636.45671800885, "count": 392692, "self": 15981.895410832716, "children": { "SubprocessEnvManager._take_step": { "total": 651.8263394138776, "count": 392692, "self": 19.18062538804952, "children": { "TorchPolicy.evaluate": { "total": 632.645714025828, "count": 718864, "self": 632.645714025828 } } }, "workers": { "total": 2.73496776225511, "count": 392691, "self": 0.0, "children": { "worker_root": { "total": 20714.13082990155, "count": 392691, "is_parallel": true, "self": 5344.687859010883, "children": { "steps_from_proto": { "total": 0.04486004274804145, "count": 58, "is_parallel": true, "self": 0.004962158505804837, "children": { "_process_rank_one_or_two_observation": { "total": 0.039897884242236614, "count": 232, "is_parallel": true, "self": 0.039897884242236614 } } }, "UnityEnvironment.step": { "total": 15369.39811084792, "count": 392691, "is_parallel": true, "self": 45.19922956766095, "children": { "UnityEnvironment._generate_step_input": { "total": 275.1343062124215, "count": 392691, "is_parallel": true, "self": 275.1343062124215 }, "communicator.exchange": { "total": 14484.499393173726, "count": 392691, "is_parallel": true, "self": 14484.499393173726 }, "steps_from_proto": { "total": 564.5651818941114, "count": 785382, "is_parallel": true, "self": 61.92030272015836, "children": { "_process_rank_one_or_two_observation": { "total": 502.6448791739531, "count": 3141528, "is_parallel": true, "self": 502.6448791739531 } } } } } } } } } } }, "trainer_advance": { "total": 4074.1221869451692, "count": 392691, "self": 36.02085299149621, "children": { "process_trajectory": { "total": 932.9670185355935, "count": 392691, "self": 931.8749483296415, "children": { "RLTrainer._checkpoint": { "total": 1.0920702059520409, "count": 11, "self": 1.0920702059520409 } } }, "_update_policy": { "total": 3105.1343154180795, "count": 275, "self": 360.8566713616019, "children": { "TorchPOCAOptimizer.update": { "total": 2744.2776440564776, "count": 8253, "self": 2744.2776440564776 } } } } } } }, "TrainerController._save_models": { "total": 0.07130979094654322, "count": 1, "self": 1.7873942852020264e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0712919170036912, "count": 1, "self": 0.0712919170036912 } } } } } } }