{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2307558059692383, "min": 3.189295530319214, "max": 3.2956700325012207, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25846.046875, "min": 17381.15625, "max": 113628.8203125, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 868.8333333333334, "min": 438.6363636363636, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20852.0, "min": 4656.0, "max": 30336.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.1698407227689, "min": 1190.897651941846, "max": 1200.8234089738921, "count": 45 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2396.3396814455377, "min": 2388.3316671163593, "max": 19054.362431069538, "count": 45 }, "SoccerTwos.Step.mean": { "value": 499622.0, "min": 9184.0, "max": 499622.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499622.0, "min": 9184.0, "max": 499622.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007917487062513828, "min": -0.021535025909543037, "max": 0.06929423660039902, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.09500984102487564, "min": -0.27282702922821045, "max": 0.9701193571090698, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007759167347103357, "min": -0.025264939293265343, "max": 0.06929536908864975, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.09311001002788544, "min": -0.3537091612815857, "max": 0.9701351523399353, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.13019999861717224, "min": -0.5, "max": 0.30142856921468464, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.562399983406067, "min": -6.0, "max": 4.219999969005585, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.13019999861717224, "min": -0.5, "max": 0.30142856921468464, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.562399983406067, "min": -6.0, "max": 4.219999969005585, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019040864354853207, "min": 0.012935439681556696, "max": 0.021922126782532685, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019040864354853207, "min": 0.012935439681556696, "max": 0.021922126782532685, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0012082137662218883, "min": 3.267044758104021e-05, "max": 0.006921788863837719, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0012082137662218883, "min": 3.267044758104021e-05, "max": 0.006921788863837719, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0012087124516256154, "min": 3.298023524015055e-05, "max": 0.00709499263515075, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0012087124516256154, "min": 3.298023524015055e-05, "max": 0.00709499263515075, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705951555", "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": "\\\\?\\F:\\Conda\\envs\\RL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1705953786" }, "total": 2230.2840806999593, "count": 1, "self": 0.8073485999484546, "children": { "run_training.setup": { "total": 0.13687530002789572, "count": 1, "self": 0.13687530002789572 }, "TrainerController.start_learning": { "total": 2229.339856799983, "count": 1, "self": 1.0265328017994761, "children": { "TrainerController._reset_env": { "total": 6.748816500068642, "count": 3, "self": 6.748816500068642 }, "TrainerController.advance": { "total": 2221.1911213981803, "count": 32618, "self": 1.1233880972722545, "children": { "env_step": { "total": 985.4585832996527, "count": 32618, "self": 770.8795617991127, "children": { "SubprocessEnvManager._take_step": { "total": 213.88915079960134, "count": 32618, "self": 7.231876100355294, "children": { "TorchPolicy.evaluate": { "total": 206.65727469924605, "count": 64782, "self": 206.65727469924605 } } }, "workers": { "total": 0.6898707009386271, "count": 32618, "self": 0.0, "children": { "worker_root": { "total": 2219.80031540012, "count": 32618, "is_parallel": true, "self": 1610.1796274032677, "children": { "steps_from_proto": { "total": 0.01154320000205189, "count": 6, "is_parallel": true, "self": 0.003289099840912968, "children": { "_process_rank_one_or_two_observation": { "total": 0.008254100161138922, "count": 24, "is_parallel": true, "self": 0.008254100161138922 } } }, "UnityEnvironment.step": { "total": 609.6091447968502, "count": 32618, "is_parallel": true, "self": 34.53558190073818, "children": { "UnityEnvironment._generate_step_input": { "total": 30.31031720264582, "count": 32618, "is_parallel": true, "self": 30.31031720264582 }, "communicator.exchange": { "total": 442.8577170924982, "count": 32618, "is_parallel": true, "self": 442.8577170924982 }, "steps_from_proto": { "total": 101.90552860096795, "count": 65236, "is_parallel": true, "self": 20.771148308413103, "children": { "_process_rank_one_or_two_observation": { "total": 81.13438029255485, "count": 260944, "is_parallel": true, "self": 81.13438029255485 } } } } } } } } } } }, "trainer_advance": { "total": 1234.6091500012553, "count": 32618, "self": 7.173557702219114, "children": { "process_trajectory": { "total": 177.4076076990459, "count": 32618, "self": 177.02247139904648, "children": { "RLTrainer._checkpoint": { "total": 0.3851362999994308, "count": 1, "self": 0.3851362999994308 } } }, "_update_policy": { "total": 1050.0279845999903, "count": 22, "self": 108.91440960031468, "children": { "TorchPOCAOptimizer.update": { "total": 941.1135749996756, "count": 672, "self": 941.1135749996756 } } } } } } }, "trainer_threads": { "total": 2.2999593056738377e-06, "count": 1, "self": 2.2999593056738377e-06 }, "TrainerController._save_models": { "total": 0.37338379997527227, "count": 1, "self": 0.02222109993454069, "children": { "RLTrainer._checkpoint": { "total": 0.3511627000407316, "count": 1, "self": 0.3511627000407316 } } } } } } }