{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1511635780334473, "min": 3.1420791149139404, "max": 3.2957353591918945, "count": 85 }, "SoccerTwos.Policy.Entropy.sum": { "value": 52032.01171875, "min": 2313.358642578125, "max": 156725.84375, "count": 85 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 411.5833333333333, "max": 999.0, "count": 85 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 11640.0, "max": 30812.0, "count": 85 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.910866615456, "min": 1194.362632659314, "max": 1205.0489266260556, "count": 68 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2397.821733230912, "min": 2388.725265318628, "max": 14460.587119512667, "count": 68 }, "SoccerTwos.Step.mean": { "value": 849908.0, "min": 9198.0, "max": 849908.0, "count": 85 }, "SoccerTwos.Step.sum": { "value": 849908.0, "min": 9198.0, "max": 849908.0, "count": 85 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006483034696429968, "min": -0.10227275639772415, "max": 0.007897152565419674, "count": 85 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.06483034789562225, "min": -1.1250003576278687, "max": 0.09425704926252365, "count": 85 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006571208126842976, "min": -0.10219087451696396, "max": 0.007881762459874153, "count": 85 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0657120794057846, "min": -1.124099612236023, "max": 0.08722180128097534, "count": 85 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 85 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 85 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6133076922538189, "max": 0.1633333365122477, "count": 85 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.972999999299645, "max": 4.059200048446655, "count": 85 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6133076922538189, "max": 0.1633333365122477, "count": 85 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.972999999299645, "max": 4.059200048446655, "count": 85 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 85 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 85 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.03053553384033612, "min": 0.027419889630497588, "max": 0.044233061406495314, "count": 74 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03053553384033612, "min": 0.027419889630497588, "max": 0.044233061406495314, "count": 74 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 8.133147203161439e-06, "min": 2.8161304637409477e-06, "max": 0.00646774370688945, "count": 74 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 8.133147203161439e-06, "min": 2.8161304637409477e-06, "max": 0.00646774370688945, "count": 74 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 8.388469354215793e-06, "min": 3.05134792465717e-06, "max": 0.006771056295838207, "count": 74 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 8.388469354215793e-06, "min": 3.05134792465717e-06, "max": 0.006771056295838207, "count": 74 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003000000000000001, "min": 0.0003, "max": 0.0003000000000000002, "count": 74 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003000000000000001, "min": 0.0003, "max": 0.0003000000000000002, "count": 74 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.16799999999999993, "min": 0.1679999999999999, "max": 0.16799999999999995, "count": 74 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.16799999999999993, "min": 0.1679999999999999, "max": 0.16799999999999995, "count": 74 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.004999999999999999, "max": 0.005000000000000001, "count": 74 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.004999999999999999, "max": 0.005000000000000001, "count": 74 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690483833", "python_version": "3.9.17 (main, Jul 5 2023, 16:17:03) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/teilomillet/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1690487377" }, "total": 3543.7497783119998, "count": 1, "self": 0.08686988099998416, "children": { "run_training.setup": { "total": 0.02692301000000019, "count": 1, "self": 0.02692301000000019 }, "TrainerController.start_learning": { "total": 3543.635985421, "count": 1, "self": 1.5595770139630076, "children": { "TrainerController._reset_env": { "total": 2.3356967650001295, "count": 5, "self": 2.3356967650001295 }, "TrainerController.advance": { "total": 3539.4445763040367, "count": 56378, "self": 1.5333378810209979, "children": { "env_step": { "total": 1127.8382332170206, "count": 56378, "self": 923.7960028720292, "children": { "SubprocessEnvManager._take_step": { "total": 203.08429541303593, "count": 56378, "self": 9.299902308051657, "children": { "TorchPolicy.evaluate": { "total": 193.78439310498428, "count": 111958, "self": 193.78439310498428 } } }, "workers": { "total": 0.9579349319554553, "count": 56378, "self": 0.0, "children": { "worker_root": { "total": 3528.700593620989, "count": 56378, "is_parallel": true, "self": 2782.433395122964, "children": { "steps_from_proto": { "total": 0.011433129000715248, "count": 10, "is_parallel": true, "self": 0.0022932900010552704, "children": { "_process_rank_one_or_two_observation": { "total": 0.009139838999659977, "count": 40, "is_parallel": true, "self": 0.009139838999659977 } } }, "UnityEnvironment.step": { "total": 746.2557653690242, "count": 56378, "is_parallel": true, "self": 41.22962596400862, "children": { "UnityEnvironment._generate_step_input": { "total": 25.237409175993662, "count": 56378, "is_parallel": true, "self": 25.237409175993662 }, "communicator.exchange": { "total": 557.1941429319934, "count": 56378, "is_parallel": true, "self": 557.1941429319934 }, "steps_from_proto": { "total": 122.59458729702845, "count": 112756, "is_parallel": true, "self": 24.86562364188363, "children": { "_process_rank_one_or_two_observation": { "total": 97.72896365514482, "count": 451024, "is_parallel": true, "self": 97.72896365514482 } } } } } } } } } } }, "trainer_advance": { "total": 2410.073005205995, "count": 56378, "self": 10.2991857410193, "children": { "process_trajectory": { "total": 278.46287342697553, "count": 56378, "self": 278.1774028799756, "children": { "RLTrainer._checkpoint": { "total": 0.2854705469999317, "count": 1, "self": 0.2854705469999317 } } }, "_update_policy": { "total": 2121.310946038, "count": 75, "self": 161.6613523550045, "children": { "TorchPOCAOptimizer.update": { "total": 1959.6495936829956, "count": 4873, "self": 1959.6495936829956 } } } } } } }, "trainer_threads": { "total": 1.7550000848132186e-06, "count": 1, "self": 1.7550000848132186e-06 }, "TrainerController._save_models": { "total": 0.296133583000028, "count": 1, "self": 0.003501777999645128, "children": { "RLTrainer._checkpoint": { "total": 0.2926318050003829, "count": 1, "self": 0.2926318050003829 } } } } } } }