{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2537543773651123, "min": 3.2069151401519775, "max": 3.2958173751831055, "count": 33 }, "SoccerTwos.Policy.Entropy.sum": { "value": 58411.3984375, "min": 24713.4296875, "max": 105466.15625, "count": 33 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 818.0, "min": 447.0, "max": 999.0, "count": 33 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19632.0, "min": 1788.0, "max": 31856.0, "count": 33 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1209.357611408545, "min": 1199.2393548497907, "max": 1209.357611408545, "count": 32 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7256.14566845127, "min": 2398.4787096995815, "max": 16919.769407736774, "count": 32 }, "SoccerTwos.Step.mean": { "value": 329724.0, "min": 9770.0, "max": 329724.0, "count": 33 }, "SoccerTwos.Step.sum": { "value": 329724.0, "min": 9770.0, "max": 329724.0, "count": 33 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0030621204059571028, "min": -0.0008333418518304825, "max": 0.07384230196475983, "count": 33 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.03674544394016266, "min": -0.015000153332948685, "max": 1.03379225730896, "count": 33 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0016769192880019546, "min": -0.0017020993400365114, "max": 0.07384181767702103, "count": 33 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.020123030990362167, "min": -0.03063778765499592, "max": 1.0337854623794556, "count": 33 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 33 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 33 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10413333773612976, "min": -0.42857142857142855, "max": 0.1590666671593984, "count": 33 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.2496000528335571, "min": -6.0, "max": 1.9088000059127808, "count": 33 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10413333773612976, "min": -0.42857142857142855, "max": 0.1590666671593984, "count": 33 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.2496000528335571, "min": -6.0, "max": 1.9088000059127808, "count": 33 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017120584277048087, "min": 0.01184630231000483, "max": 0.020048254150606227, "count": 15 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017120584277048087, "min": 0.01184630231000483, "max": 0.020048254150606227, "count": 15 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0025950087544818717, "min": 0.0006825556454714387, "max": 0.004943428281694651, "count": 15 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0025950087544818717, "min": 0.0006825556454714387, "max": 0.004943428281694651, "count": 15 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002597692298392455, "min": 0.0006826190966724728, "max": 0.0050204995010669036, "count": 15 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002597692298392455, "min": 0.0006826190966724728, "max": 0.0050204995010669036, "count": 15 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00020000000000000004, "count": 15 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00020000000000000004, "count": 15 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 15 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 15 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.01, "max": 0.010000000000000002, "count": 15 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.01, "max": 0.010000000000000002, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683405461", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "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": "1683406974" }, "total": 1512.703789291, "count": 1, "self": 0.1597869570000512, "children": { "run_training.setup": { "total": 0.05548366699999985, "count": 1, "self": 0.05548366699999985 }, "TrainerController.start_learning": { "total": 1512.4885186669999, "count": 1, "self": 0.25970882700585207, "children": { "TrainerController._reset_env": { "total": 2.2931211249999333, "count": 2, "self": 2.2931211249999333 }, "TrainerController.advance": { "total": 1509.782210796994, "count": 21579, "self": 0.24726577001251826, "children": { "env_step": { "total": 1238.8051764919874, "count": 21579, "self": 1195.3630238779756, "children": { "SubprocessEnvManager._take_step": { "total": 43.25285580400478, "count": 21579, "self": 1.2754701040110632, "children": { "TorchPolicy.evaluate": { "total": 41.97738569999372, "count": 42860, "self": 41.97738569999372 } } }, "workers": { "total": 0.1892968100068888, "count": 21578, "self": 0.0, "children": { "worker_root": { "total": 1509.6495894130055, "count": 21578, "is_parallel": true, "self": 349.4384122730048, "children": { "steps_from_proto": { "total": 0.0037250000000343952, "count": 4, "is_parallel": true, "self": 0.0005595840002534658, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031654159997809295, "count": 16, "is_parallel": true, "self": 0.0031654159997809295 } } }, "UnityEnvironment.step": { "total": 1160.2074521400007, "count": 21578, "is_parallel": true, "self": 3.0327681719870725, "children": { "UnityEnvironment._generate_step_input": { "total": 20.090124248995796, "count": 21578, "is_parallel": true, "self": 20.090124248995796 }, "communicator.exchange": { "total": 1094.6483185990135, "count": 21578, "is_parallel": true, "self": 1094.6483185990135 }, "steps_from_proto": { "total": 42.43624112000441, "count": 43156, "is_parallel": true, "self": 4.705739092995032, "children": { "_process_rank_one_or_two_observation": { "total": 37.73050202700938, "count": 172624, "is_parallel": true, "self": 37.73050202700938 } } } } } } } } } } }, "trainer_advance": { "total": 270.7297685349941, "count": 21578, "self": 2.1676305409926613, "children": { "process_trajectory": { "total": 37.25934370100136, "count": 21578, "self": 37.25934370100136 }, "_update_policy": { "total": 231.30279429300006, "count": 15, "self": 29.242100787998396, "children": { "TorchPOCAOptimizer.update": { "total": 202.06069350500167, "count": 462, "self": 202.06069350500167 } } } } } } }, "trainer_threads": { "total": 5.840001904289238e-07, "count": 1, "self": 5.840001904289238e-07 }, "TrainerController._save_models": { "total": 0.15347733399994468, "count": 1, "self": 0.005591333999973358, "children": { "RLTrainer._checkpoint": { "total": 0.14788599999997132, "count": 1, "self": 0.14788599999997132 } } } } } } }