{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8799536228179932, "min": 1.8550299406051636, "max": 3.2957143783569336, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38140.5, "min": 13597.73828125, "max": 114579.84375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.19230769230769, "min": 45.03669724770642, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19632.0, "min": 11468.0, "max": 29272.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1573.3306224513833, "min": 1189.222707025258, "max": 1595.6328559795825, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327252.7694698877, "min": 2381.229202148366, "max": 346679.98105892615, "count": 500 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9654.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9654.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02874203957617283, "min": -0.09531740099191666, "max": 0.18036769330501556, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.949602127075195, "min": -17.347766876220703, "max": 26.333683013916016, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03399577736854553, "min": -0.10003126412630081, "max": 0.1756085902452469, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.037125587463379, "min": -18.205690383911133, "max": 25.63885498046875, "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": 0.0746473431011329, "min": -0.6153846153846154, "max": 0.4446842105765092, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.45200002193451, "min": -53.72039979696274, "max": 55.82599949836731, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0746473431011329, "min": -0.6153846153846154, "max": 0.4446842105765092, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.45200002193451, "min": -53.72039979696274, "max": 55.82599949836731, "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": 0.0184247207439815, "min": 0.011243180965539067, "max": 0.024702083909263213, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0184247207439815, "min": 0.011243180965539067, "max": 0.024702083909263213, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11222326507170995, "min": 0.0017094490079519649, "max": 0.12109096869826316, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11222326507170995, "min": 0.0017094490079519649, "max": 0.12109096869826316, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11396088898181915, "min": 0.0017675870156381279, "max": 0.1225358285009861, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11396088898181915, "min": 0.0017675870156381279, "max": 0.1225358285009861, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688450896", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/sid/anaconda3/envs/unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688456373" }, "total": 5477.754930863011, "count": 1, "self": 0.21783111200784333, "children": { "run_training.setup": { "total": 0.007659700000658631, "count": 1, "self": 0.007659700000658631 }, "TrainerController.start_learning": { "total": 5477.529440051003, "count": 1, "self": 4.779532408138039, "children": { "TrainerController._reset_env": { "total": 2.9950538479315583, "count": 25, "self": 2.9950538479315583 }, "TrainerController.advance": { "total": 5469.602809899923, "count": 337563, "self": 4.833934164373204, "children": { "env_step": { "total": 4201.1555099783, "count": 337563, "self": 3273.0911253134836, "children": { "SubprocessEnvManager._take_step": { "total": 925.0884008085122, "count": 337563, "self": 24.83674777444685, "children": { "TorchPolicy.evaluate": { "total": 900.2516530340654, "count": 631008, "self": 900.2516530340654 } } }, "workers": { "total": 2.975983856304083, "count": 337563, "self": 0.0, "children": { "worker_root": { "total": 5471.790534255386, "count": 337563, "is_parallel": true, "self": 2724.651954491419, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001616532012121752, "count": 2, "is_parallel": true, "self": 0.0003781510458793491, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012383809662424028, "count": 8, "is_parallel": true, "self": 0.0012383809662424028 } } }, "UnityEnvironment.step": { "total": 0.017639169993344694, "count": 1, "is_parallel": true, "self": 0.0003497930010780692, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000279981002677232, "count": 1, "is_parallel": true, "self": 0.000279981002677232 }, "communicator.exchange": { "total": 0.015890065988060087, "count": 1, "is_parallel": true, "self": 0.015890065988060087 }, "steps_from_proto": { "total": 0.0011193300015293062, "count": 2, "is_parallel": true, "self": 0.0002406440326012671, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008786859689280391, "count": 8, "is_parallel": true, "self": 0.0008786859689280391 } } } } } } }, "UnityEnvironment.step": { "total": 2747.1096751400037, "count": 337562, "is_parallel": true, "self": 145.09935216236045, "children": { "UnityEnvironment._generate_step_input": { "total": 77.60536548917298, "count": 337562, "is_parallel": true, "self": 77.60536548917298 }, "communicator.exchange": { "total": 2122.4780113258166, "count": 337562, "is_parallel": true, "self": 2122.4780113258166 }, "steps_from_proto": { "total": 401.9269461626536, "count": 675124, "is_parallel": true, "self": 74.75567241510726, "children": { "_process_rank_one_or_two_observation": { "total": 327.17127374754637, "count": 2700496, "is_parallel": true, "self": 327.17127374754637 } } } } }, "steps_from_proto": { "total": 0.028904623963171616, "count": 48, "is_parallel": true, "self": 0.005636942281853408, "children": { "_process_rank_one_or_two_observation": { "total": 0.02326768168131821, "count": 192, "is_parallel": true, "self": 0.02326768168131821 } } } } } } } } }, "trainer_advance": { "total": 1263.61336575725, "count": 337563, "self": 34.30502635330777, "children": { "process_trajectory": { "total": 491.4585799726483, "count": 337563, "self": 489.93451861065114, "children": { "RLTrainer._checkpoint": { "total": 1.5240613619971555, "count": 10, "self": 1.5240613619971555 } } }, "_update_policy": { "total": 737.8497594312939, "count": 240, "self": 471.48287271353183, "children": { "TorchPOCAOptimizer.update": { "total": 266.3668867177621, "count": 7200, "self": 266.3668867177621 } } } } } } }, "trainer_threads": { "total": 5.500041879713535e-07, "count": 1, "self": 5.500041879713535e-07 }, "TrainerController._save_models": { "total": 0.15204334500594996, "count": 1, "self": 0.0014920849935151637, "children": { "RLTrainer._checkpoint": { "total": 0.1505512600124348, "count": 1, "self": 0.1505512600124348 } } } } } } }