{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4289458990097046, "min": 1.3331218957901, "max": 3.295753002166748, "count": 2909 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28441.740234375, "min": 14116.41015625, "max": 134564.359375, "count": 2909 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.63636363636364, "min": 38.728, "max": 999.0, "count": 2909 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19176.0, "min": 1368.0, "max": 33472.0, "count": 2909 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1633.2024141553666, "min": 1197.4528454987494, "max": 1700.748415074803, "count": 2894 }, "SoccerTwos.Self-play.ELO.sum": { "value": 215582.71866850837, "min": 2395.855516605603, "max": 399412.78237338376, "count": 2894 }, "SoccerTwos.Step.mean": { "value": 29089880.0, "min": 9034.0, "max": 29089880.0, "count": 2909 }, "SoccerTwos.Step.sum": { "value": 29089880.0, "min": 9034.0, "max": 29089880.0, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016269130632281303, "min": -0.14047899842262268, "max": 0.18399012088775635, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.1475253105163574, "min": -23.84164047241211, "max": 26.68563461303711, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01794874481856823, "min": -0.1390056312084198, "max": 0.18372780084609985, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.369234323501587, "min": -24.460636138916016, "max": 26.59808349609375, "count": 2909 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2909 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04186969814878522, "min": -0.5260500013828278, "max": 0.5829966128882715, "count": 2909 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.526800155639648, "min": -81.90319991111755, "max": 53.70960021018982, "count": 2909 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04186969814878522, "min": -0.5260500013828278, "max": 0.5829966128882715, "count": 2909 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.526800155639648, "min": -81.90319991111755, "max": 53.70960021018982, "count": 2909 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2909 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2909 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017092395084910096, "min": 0.010334619101680194, "max": 0.02452780718158465, "count": 1409 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017092395084910096, "min": 0.010334619101680194, "max": 0.02452780718158465, "count": 1409 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08425002073248228, "min": 4.625412599731741e-05, "max": 0.132067218174537, "count": 1409 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08425002073248228, "min": 4.625412599731741e-05, "max": 0.132067218174537, "count": 1409 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0861614927649498, "min": 4.70900532794379e-05, "max": 0.13552140071988106, "count": 1409 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0861614927649498, "min": 4.70900532794379e-05, "max": 0.13552140071988106, "count": 1409 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1409 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1409 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1409 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1409 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1409 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1409 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691727176", "python_version": "3.9.17 (main, Jul 5 2023, 21:05:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/renatostrianese/anaconda3/envs/RenatoTF/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwo/SoccerTwos.x86_64 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691805708" }, "total": 78532.367960672, "count": 1, "self": 0.06609775401011575, "children": { "run_training.setup": { "total": 0.03313046699622646, "count": 1, "self": 0.03313046699622646 }, "TrainerController.start_learning": { "total": 78532.26873245099, "count": 1, "self": 47.53482574840018, "children": { "TrainerController._reset_env": { "total": 4.610130590015615, "count": 146, "self": 4.610130590015615 }, "TrainerController.advance": { "total": 78479.86887295157, "count": 2012113, "self": 46.898810708808014, "children": { "env_step": { "total": 35817.85841291145, "count": 2012113, "self": 30057.72681538717, "children": { "SubprocessEnvManager._take_step": { "total": 5729.997554799687, "count": 2012113, "self": 223.7001909118626, "children": { "TorchPolicy.evaluate": { "total": 5506.297363887825, "count": 3654072, "self": 5506.297363887825 } } }, "workers": { "total": 30.13404272459593, "count": 2012112, "self": 0.0, "children": { "worker_root": { "total": 78466.91669943526, "count": 2012112, "is_parallel": true, "self": 53690.49747905135, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031258160015568137, "count": 2, "is_parallel": true, "self": 0.0009946089994627982, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021312070020940155, "count": 8, "is_parallel": true, "self": 0.0021312070020940155 } } }, "UnityEnvironment.step": { "total": 0.028206431001308374, "count": 1, "is_parallel": true, "self": 0.0005391929953475483, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004178079980192706, "count": 1, "is_parallel": true, "self": 0.0004178079980192706 }, "communicator.exchange": { "total": 0.025404737003555056, "count": 1, "is_parallel": true, "self": 0.025404737003555056 }, "steps_from_proto": { "total": 0.0018446930043864995, "count": 2, "is_parallel": true, "self": 0.0004180240066489205, "children": { "_process_rank_one_or_two_observation": { "total": 0.001426668997737579, "count": 8, "is_parallel": true, "self": 0.001426668997737579 } } } } } } }, "UnityEnvironment.step": { "total": 24776.102041746977, "count": 2012111, "is_parallel": true, "self": 1435.6359346336321, "children": { "UnityEnvironment._generate_step_input": { "total": 1037.9718928028597, "count": 2012111, "is_parallel": true, "self": 1037.9718928028597 }, "communicator.exchange": { "total": 17808.430640130806, "count": 2012111, "is_parallel": true, "self": 17808.430640130806 }, "steps_from_proto": { "total": 4494.06357417968, "count": 4024222, "is_parallel": true, "self": 863.1041507397385, "children": { "_process_rank_one_or_two_observation": { "total": 3630.959423439941, "count": 16096888, "is_parallel": true, "self": 3630.959423439941 } } } } }, "steps_from_proto": { "total": 0.3171786369275651, "count": 290, "is_parallel": true, "self": 0.06221032103348989, "children": { "_process_rank_one_or_two_observation": { "total": 0.2549683158940752, "count": 1160, "is_parallel": true, "self": 0.2549683158940752 } } } } } } } } }, "trainer_advance": { "total": 42615.11164933131, "count": 2012112, "self": 298.4929725266047, "children": { "process_trajectory": { "total": 6410.776937356939, "count": 2012112, "self": 6396.632048044943, "children": { "RLTrainer._checkpoint": { "total": 14.14488931199594, "count": 58, "self": 14.14488931199594 } } }, "_update_policy": { "total": 35905.841739447766, "count": 1409, "self": 4567.986399615293, "children": { "TorchPOCAOptimizer.update": { "total": 31337.855339832473, "count": 42285, "self": 31337.855339832473 } } } } } } }, "trainer_threads": { "total": 1.69100530911237e-06, "count": 1, "self": 1.69100530911237e-06 }, "TrainerController._save_models": { "total": 0.2549014700052794, "count": 1, "self": 0.002151414009858854, "children": { "RLTrainer._checkpoint": { "total": 0.25275005599542055, "count": 1, "self": 0.25275005599542055 } } } } } } }