{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8774759769439697, "min": 1.8230854272842407, "max": 3.2957592010498047, "count": 650 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37369.28125, "min": 31598.404296875, "max": 125238.84375, "count": 650 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.14473684210526, "min": 45.39449541284404, "max": 999.0, "count": 650 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19804.0, "min": 12808.0, "max": 28468.0, "count": 650 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1657.5226141061385, "min": 1198.7535925691843, "max": 1657.5226141061385, "count": 644 }, "SoccerTwos.Self-play.ELO.sum": { "value": 251943.43734413304, "min": 2403.7680185623153, "max": 347966.3823908464, "count": 644 }, "SoccerTwos.Step.mean": { "value": 6499982.0, "min": 9250.0, "max": 6499982.0, "count": 650 }, "SoccerTwos.Step.sum": { "value": 6499982.0, "min": 9250.0, "max": 6499982.0, "count": 650 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03020160272717476, "min": -0.1315937340259552, "max": 0.31489238142967224, "count": 650 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.560441970825195, "min": -19.592727661132812, "max": 42.04832458496094, "count": 650 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.028834901750087738, "min": -0.13370631635189056, "max": 0.3127575218677521, "count": 650 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.35407018661499, "min": -19.63623809814453, "max": 42.27655029296875, "count": 650 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 650 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 650 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08127682335329371, "min": -0.5777799993753433, "max": 0.5952825366504608, "count": 650 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -12.272800326347351, "min": -50.421999633312225, "max": 86.74399983882904, "count": 650 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08127682335329371, "min": -0.5777799993753433, "max": 0.5952825366504608, "count": 650 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -12.272800326347351, "min": -50.421999633312225, "max": 86.74399983882904, "count": 650 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 650 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 650 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015245077373522993, "min": 0.010870925474834318, "max": 0.024924556460852423, "count": 313 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015245077373522993, "min": 0.010870925474834318, "max": 0.024924556460852423, "count": 313 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09139621928334236, "min": 0.00011678574228426441, "max": 0.11551008224487305, "count": 313 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09139621928334236, "min": 0.00011678574228426441, "max": 0.11551008224487305, "count": 313 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09248334566752116, "min": 0.00012518015209934675, "max": 0.11676155601938566, "count": 313 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09248334566752116, "min": 0.00012518015209934675, "max": 0.11676155601938566, "count": 313 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 313 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 313 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 313 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 313 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 313 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 313 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727099394", "python_version": "3.10.12 (main, Sep 23 2024, 16:48:48) [GCC 11.4.0]", "command_line_arguments": "/home/smitsis/deep_rl/unit7/ml-agents/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1727114671" }, "total": 15277.358717189998, "count": 1, "self": 0.2107879139985016, "children": { "run_training.setup": { "total": 0.014571755000361009, "count": 1, "self": 0.014571755000361009 }, "TrainerController.start_learning": { "total": 15277.133357521, "count": 1, "self": 13.382955916942592, "children": { "TrainerController._reset_env": { "total": 3.1114011030058464, "count": 19, "self": 3.1114011030058464 }, "TrainerController.advance": { "total": 15260.148709124049, "count": 442889, "self": 13.362418611493922, "children": { "env_step": { "total": 10468.270577584424, "count": 442889, "self": 5768.788711935371, "children": { "SubprocessEnvManager._take_step": { "total": 4692.116632672116, "count": 442889, "self": 80.83054285169055, "children": { "TorchPolicy.evaluate": { "total": 4611.286089820425, "count": 816546, "self": 4611.286089820425 } } }, "workers": { "total": 7.365232976937477, "count": 442889, "self": 0.0, "children": { "worker_root": { "total": 15258.663917305925, "count": 442889, "is_parallel": true, "self": 10963.82709216906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016971800014289329, "count": 2, "is_parallel": true, "self": 0.0005622120061161695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011349679953127634, "count": 8, "is_parallel": true, "self": 0.0011349679953127634 } } }, "UnityEnvironment.step": { "total": 0.021635789998981636, "count": 1, "is_parallel": true, "self": 0.0004916239977319492, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006636550006078323, "count": 1, "is_parallel": true, "self": 0.0006636550006078323 }, "communicator.exchange": { "total": 0.01868441599981452, "count": 1, "is_parallel": true, "self": 0.01868441599981452 }, "steps_from_proto": { "total": 0.0017960950008273358, "count": 2, "is_parallel": true, "self": 0.0004361360006441828, "children": { "_process_rank_one_or_two_observation": { "total": 0.001359959000183153, "count": 8, "is_parallel": true, "self": 0.001359959000183153 } } } } } } }, "UnityEnvironment.step": { "total": 4294.809464913864, "count": 442888, "is_parallel": true, "self": 180.9360052807133, "children": { "UnityEnvironment._generate_step_input": { "total": 204.9597975631732, "count": 442888, "is_parallel": true, "self": 204.9597975631732 }, "communicator.exchange": { "total": 3274.868720286333, "count": 442888, "is_parallel": true, "self": 3274.868720286333 }, "steps_from_proto": { "total": 634.0449417836444, "count": 885776, "is_parallel": true, "self": 149.30680120312172, "children": { "_process_rank_one_or_two_observation": { "total": 484.73814058052267, "count": 3543104, "is_parallel": true, "self": 484.73814058052267 } } } } }, "steps_from_proto": { "total": 0.027360223000869155, "count": 36, "is_parallel": true, "self": 0.006583262016647495, "children": { "_process_rank_one_or_two_observation": { "total": 0.02077696098422166, "count": 144, "is_parallel": true, "self": 0.02077696098422166 } } } } } } } } }, "trainer_advance": { "total": 4778.515712928131, "count": 442889, "self": 91.62737726339401, "children": { "process_trajectory": { "total": 1949.8084437717662, "count": 442889, "self": 1944.7308315997652, "children": { "RLTrainer._checkpoint": { "total": 5.077612172000954, "count": 13, "self": 5.077612172000954 } } }, "_update_policy": { "total": 2737.0798918929704, "count": 313, "self": 1955.5204607951237, "children": { "TorchPOCAOptimizer.update": { "total": 781.5594310978468, "count": 9390, "self": 781.5594310978468 } } } } } } }, "trainer_threads": { "total": 1.3899989426136017e-06, "count": 1, "self": 1.3899989426136017e-06 }, "TrainerController._save_models": { "total": 0.4902899870030524, "count": 1, "self": 0.015460426002391614, "children": { "RLTrainer._checkpoint": { "total": 0.47482956100066076, "count": 1, "self": 0.47482956100066076 } } } } } } }