{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2785375118255615, "min": 3.277444839477539, "max": 3.2957262992858887, "count": 6 }, "SoccerTwos.Policy.Entropy.sum": { "value": 72390.109375, "min": 59465.9609375, "max": 105463.2421875, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 763.3333333333334, "min": 573.0, "max": 965.6, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18320.0, "min": 16044.0, "max": 25552.0, "count": 6 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.3483737537852, "min": 1197.969354398465, "max": 1201.2421091626256, "count": 6 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4793.393495015141, "min": 2395.93870879693, "max": 12010.233231809583, "count": 6 }, "SoccerTwos.Step.mean": { "value": 59100.0, "min": 9622.0, "max": 59100.0, "count": 6 }, "SoccerTwos.Step.sum": { "value": 59100.0, "min": 9622.0, "max": 59100.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005940200760960579, "min": -0.005940200760960579, "max": 0.004564695525914431, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.07128240913152695, "min": -0.07128240913152695, "max": 0.07303512841463089, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009806621819734573, "min": -0.009806621819734573, "max": 0.004620045889168978, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.11767946183681488, "min": -0.11767946183681488, "max": 0.07392073422670364, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08463333547115326, "min": -0.28404999896883965, "max": 0.06803077000838059, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.0156000256538391, "min": -4.544799983501434, "max": 0.8844000101089478, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08463333547115326, "min": -0.28404999896883965, "max": 0.06803077000838059, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.0156000256538391, "min": -4.544799983501434, "max": 0.8844000101089478, "count": 6 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019398090445126095, "min": 0.016044788503980573, "max": 0.019398090445126095, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019398090445126095, "min": 0.016044788503980573, "max": 0.019398090445126095, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0023252678258965415, "min": 0.0023252678258965415, "max": 0.004639482009224594, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0023252678258965415, "min": 0.0023252678258965415, "max": 0.004639482009224594, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002352929871995002, "min": 0.002352929871995002, "max": 0.004379451057563225, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002352929871995002, "min": 0.002352929871995002, "max": 0.004379451057563225, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712087786", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\aleks\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --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": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1712088191" }, "total": 405.1943989000283, "count": 1, "self": 0.14406610000878572, "children": { "run_training.setup": { "total": 0.11985490005463362, "count": 1, "self": 0.11985490005463362 }, "TrainerController.start_learning": { "total": 404.9304778999649, "count": 1, "self": 0.24851249251514673, "children": { "TrainerController._reset_env": { "total": 9.009788099909201, "count": 1, "self": 9.009788099909201 }, "TrainerController.advance": { "total": 395.36254320759326, "count": 4710, "self": 0.267906513530761, "children": { "env_step": { "total": 217.6248510950245, "count": 4710, "self": 169.99283299548551, "children": { "SubprocessEnvManager._take_step": { "total": 47.47341290069744, "count": 4710, "self": 1.4736969931982458, "children": { "TorchPolicy.evaluate": { "total": 45.999715907499194, "count": 9360, "self": 45.999715907499194 } } }, "workers": { "total": 0.158605198841542, "count": 4709, "self": 0.0, "children": { "worker_root": { "total": 398.56799059710465, "count": 4709, "is_parallel": true, "self": 261.24058149009943, "children": { "steps_from_proto": { "total": 0.0022142999805510044, "count": 2, "is_parallel": true, "self": 0.000512799946591258, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017015000339597464, "count": 8, "is_parallel": true, "self": 0.0017015000339597464 } } }, "UnityEnvironment.step": { "total": 137.32519480702467, "count": 4709, "is_parallel": true, "self": 6.884166902163997, "children": { "UnityEnvironment._generate_step_input": { "total": 5.627807593438774, "count": 4709, "is_parallel": true, "self": 5.627807593438774 }, "communicator.exchange": { "total": 102.31391689740121, "count": 4709, "is_parallel": true, "self": 102.31391689740121 }, "steps_from_proto": { "total": 22.499303414020687, "count": 9418, "is_parallel": true, "self": 4.497028919635341, "children": { "_process_rank_one_or_two_observation": { "total": 18.002274494385347, "count": 37672, "is_parallel": true, "self": 18.002274494385347 } } } } } } } } } } }, "trainer_advance": { "total": 177.469785599038, "count": 4709, "self": 1.959788104519248, "children": { "process_trajectory": { "total": 28.999189694644883, "count": 4709, "self": 28.999189694644883 }, "_update_policy": { "total": 146.51080779987387, "count": 3, "self": 15.312781100627035, "children": { "TorchPOCAOptimizer.update": { "total": 131.19802669924684, "count": 90, "self": 131.19802669924684 } } } } } } }, "trainer_threads": { "total": 2.400018274784088e-06, "count": 1, "self": 2.400018274784088e-06 }, "TrainerController._save_models": { "total": 0.30963169992901385, "count": 1, "self": 0.003585000056773424, "children": { "RLTrainer._checkpoint": { "total": 0.3060466998722404, "count": 1, "self": 0.3060466998722404 } } } } } } }