{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4086549282073975, "min": 1.268043875694275, "max": 3.295724630355835, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28759.099609375, "min": 21151.21484375, "max": 111021.765625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 79.79032258064517, "min": 41.63247863247863, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19788.0, "min": 9664.0, "max": 31244.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1829.12120939836, "min": 1191.1156991376893, "max": 1906.1469234347953, "count": 4994 }, "SoccerTwos.Self-play.ELO.sum": { "value": 226811.02996539662, "min": 2383.338683115511, "max": 430477.6972377616, "count": 4994 }, "SoccerTwos.Step.mean": { "value": 49999945.0, "min": 9638.0, "max": 49999945.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999945.0, "min": 9638.0, "max": 49999945.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03521855175495148, "min": -0.165052130818367, "max": 0.23691850900650024, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.367100238800049, "min": -26.408340454101562, "max": 35.004268646240234, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.034728504717350006, "min": -0.1632629930973053, "max": 0.23600859940052032, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.306334495544434, "min": -26.122079849243164, "max": 33.70362091064453, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1485548355887013, "min": -0.638063160996688, "max": 0.43167058860554414, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.420799612998962, "min": -66.41400015354156, "max": 64.83860021829605, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1485548355887013, "min": -0.638063160996688, "max": 0.43167058860554414, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.420799612998962, "min": -66.41400015354156, "max": 64.83860021829605, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019478699524188414, "min": 0.00937927095995595, "max": 0.025816674375285707, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019478699524188414, "min": 0.00937927095995595, "max": 0.025816674375285707, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08596547668178876, "min": 0.00021378911915235222, "max": 0.12492119148373604, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08596547668178876, "min": 0.00021378911915235222, "max": 0.12492119148373604, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08699496537446975, "min": 0.00021644697577964203, "max": 0.12640473643938702, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08699496537446975, "min": 0.00021644697577964203, "max": 0.12640473643938702, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698650611", "python_version": "3.10.10 | packaged by Anaconda, Inc. | (main, Mar 21 2023, 18:39:17) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Ignacio\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=ScoeerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1698743886" }, "total": 93274.29332550001, "count": 1, "self": 0.27556440002808813, "children": { "run_training.setup": { "total": 0.07127410000248346, "count": 1, "self": 0.07127410000248346 }, "TrainerController.start_learning": { "total": 93273.94648699998, "count": 1, "self": 58.83607880471391, "children": { "TrainerController._reset_env": { "total": 8.17233990020759, "count": 250, "self": 8.17233990020759 }, "TrainerController.advance": { "total": 93206.82897949505, "count": 3448391, "self": 52.582258994531, "children": { "env_step": { "total": 39581.76548850494, "count": 3448391, "self": 30913.340164013513, "children": { "SubprocessEnvManager._take_step": { "total": 8633.625579697109, "count": 3448391, "self": 321.80235908659233, "children": { "TorchPolicy.evaluate": { "total": 8311.823220610517, "count": 6280544, "self": 8311.823220610517 } } }, "workers": { "total": 34.79974479431985, "count": 3448391, "self": 0.0, "children": { "worker_root": { "total": 93202.42310158622, "count": 3448391, "is_parallel": true, "self": 68869.10959709574, "children": { "steps_from_proto": { "total": 0.29738700023153797, "count": 500, "is_parallel": true, "self": 0.06373980031639803, "children": { "_process_rank_one_or_two_observation": { "total": 0.23364719991513994, "count": 2000, "is_parallel": true, "self": 0.23364719991513994 } } }, "UnityEnvironment.step": { "total": 24333.016117490246, "count": 3448391, "is_parallel": true, "self": 1171.1086369622499, "children": { "UnityEnvironment._generate_step_input": { "total": 997.1881673770258, "count": 3448391, "is_parallel": true, "self": 997.1881673770258 }, "communicator.exchange": { "total": 18612.42163566519, "count": 3448391, "is_parallel": true, "self": 18612.42163566519 }, "steps_from_proto": { "total": 3552.2976774857816, "count": 6896782, "is_parallel": true, "self": 734.322668517023, "children": { "_process_rank_one_or_two_observation": { "total": 2817.9750089687586, "count": 27587128, "is_parallel": true, "self": 2817.9750089687586 } } } } } } } } } } }, "trainer_advance": { "total": 53572.48123199558, "count": 3448391, "self": 498.42538041890657, "children": { "process_trajectory": { "total": 10664.200104576332, "count": 3448391, "self": 10653.466261676323, "children": { "RLTrainer._checkpoint": { "total": 10.733842900008312, "count": 100, "self": 10.733842900008312 } } }, "_update_policy": { "total": 42409.85574700034, "count": 2425, "self": 6294.645024598241, "children": { "TorchPOCAOptimizer.update": { "total": 36115.2107224021, "count": 72759, "self": 36115.2107224021 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.10908799999742769, "count": 1, "self": 0.004449700005352497, "children": { "RLTrainer._checkpoint": { "total": 0.10463829999207519, "count": 1, "self": 0.10463829999207519 } } } } } } }