{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.318866491317749, "min": 2.281125545501709, "max": 3.295729160308838, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44967.45703125, "min": 21503.2421875, "max": 114055.9375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.61797752808989, "min": 40.21311475409836, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19444.0, "min": 11816.0, "max": 28160.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1444.241350433996, "min": 1188.6479357620524, "max": 1452.95869128405, "count": 457 }, "SoccerTwos.Self-play.ELO.sum": { "value": 257074.96037725132, "min": 2377.2958715241048, "max": 333759.33162617043, "count": 457 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9098.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9098.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01115392055362463, "min": -0.0824785977602005, "max": 0.1251400262117386, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.9853978157043457, "min": -17.485462188720703, "max": 26.71692657470703, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0083291195333004, "min": -0.08574127405881882, "max": 0.12677337229251862, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.4825832843780518, "min": -18.17715072631836, "max": 27.129501342773438, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.025107865253191315, "min": -0.5714285714285714, "max": 0.3720830150370328, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.469200015068054, "min": -45.066800117492676, "max": 44.236600160598755, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.025107865253191315, "min": -0.5714285714285714, "max": 0.3720830150370328, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.469200015068054, "min": -45.066800117492676, "max": 44.236600160598755, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01991559787808607, "min": 0.009667840918700677, "max": 0.025319089300561853, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01991559787808607, "min": 0.009667840918700677, "max": 0.025319089300561853, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0988339307407538, "min": 1.0261525767418789e-05, "max": 0.10845122387011846, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0988339307407538, "min": 1.0261525767418789e-05, "max": 0.10845122387011846, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10113530655701955, "min": 9.740641371536184e-06, "max": 0.11117829009890556, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10113530655701955, "min": 9.740641371536184e-06, "max": 0.11117829009890556, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699119567", "python_version": "3.10.12 (main, Nov 3 2023, 10:20:14) [Clang 15.0.0 (clang-1500.0.40.1)]", "command_line_arguments": "/Users/mariana/.pyenv/versions/hf-mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0", "numpy_version": "1.21.2", "end_time_seconds": "1699139322" }, "total": 19754.784502083, "count": 1, "self": 0.24437058297917247, "children": { "run_training.setup": { "total": 0.02322391699999571, "count": 1, "self": 0.02322391699999571 }, "TrainerController.start_learning": { "total": 19754.51690758302, "count": 1, "self": 4.011302950850222, "children": { "TrainerController._reset_env": { "total": 4.623153710999759, "count": 25, "self": 4.623153710999759 }, "TrainerController.advance": { "total": 19745.780157337198, "count": 333456, "self": 3.4934298787557054, "children": { "env_step": { "total": 16002.080422994419, "count": 333456, "self": 15398.512569719896, "children": { "SubprocessEnvManager._take_step": { "total": 601.0362062355562, "count": 333456, "self": 18.547572769370163, "children": { "TorchPolicy.evaluate": { "total": 582.488633466186, "count": 638470, "self": 582.488633466186 } } }, "workers": { "total": 2.5316470389661845, "count": 333456, "self": 0.0, "children": { "worker_root": { "total": 19744.835674227506, "count": 333456, "is_parallel": true, "self": 4873.171419823164, "children": { "steps_from_proto": { "total": 0.03967812395421788, "count": 50, "is_parallel": true, "self": 0.004709505650680512, "children": { "_process_rank_one_or_two_observation": { "total": 0.03496861830353737, "count": 200, "is_parallel": true, "self": 0.03496861830353737 } } }, "UnityEnvironment.step": { "total": 14871.624576280388, "count": 333456, "is_parallel": true, "self": 40.67991027238895, "children": { "UnityEnvironment._generate_step_input": { "total": 260.0782363534381, "count": 333456, "is_parallel": true, "self": 260.0782363534381 }, "communicator.exchange": { "total": 14046.592645224591, "count": 333456, "is_parallel": true, "self": 14046.592645224591 }, "steps_from_proto": { "total": 524.27378442997, "count": 666912, "is_parallel": true, "self": 60.76829427227494, "children": { "_process_rank_one_or_two_observation": { "total": 463.505490157695, "count": 2667648, "is_parallel": true, "self": 463.505490157695 } } } } } } } } } } }, "trainer_advance": { "total": 3740.2063044640236, "count": 333456, "self": 37.917903069755994, "children": { "process_trajectory": { "total": 703.8874651051883, "count": 333456, "self": 702.7401225632348, "children": { "RLTrainer._checkpoint": { "total": 1.1473425419535488, "count": 10, "self": 1.1473425419535488 } } }, "_update_policy": { "total": 2998.4009362890793, "count": 237, "self": 453.46624880400486, "children": { "TorchPOCAOptimizer.update": { "total": 2544.9346874850744, "count": 7110, "self": 2544.9346874850744 } } } } } } }, "trainer_threads": { "total": 3.33995558321476e-07, "count": 1, "self": 3.33995558321476e-07 }, "TrainerController._save_models": { "total": 0.10229324997635558, "count": 1, "self": 0.0019287089817225933, "children": { "RLTrainer._checkpoint": { "total": 0.10036454099463299, "count": 1, "self": 0.10036454099463299 } } } } } } }