{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7387030124664307, "min": 1.602759599685669, "max": 2.2985939979553223, "count": 2616 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33995.12109375, "min": 29153.87109375, "max": 52195.80078125, "count": 2616 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.31506849315069, "min": 42.05128205128205, "max": 98.1, "count": 2616 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19656.0, "min": 11968.0, "max": 21624.0, "count": 2616 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1647.0145821342098, "min": 1523.1757923631521, "max": 1683.1263579667557, "count": 2616 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240464.12899159463, "min": 161976.6178275062, "max": 375234.1630738749, "count": 2616 }, "SoccerTwos.Step.mean": { "value": 57319984.0, "min": 31169946.0, "max": 57319984.0, "count": 2616 }, "SoccerTwos.Step.sum": { "value": 57319984.0, "min": 31169946.0, "max": 57319984.0, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.026573531329631805, "min": -0.08645182847976685, "max": 0.09884937852621078, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.8797357082366943, "min": -16.723806381225586, "max": 17.298641204833984, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026755662634968758, "min": -0.08634110540151596, "max": 0.09761469066143036, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.9063267707824707, "min": -16.491151809692383, "max": 17.082571029663086, "count": 2616 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2616 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2032150691502715, "min": -0.33299006179252766, "max": 0.3775018179055416, "count": 2616 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -29.669400095939636, "min": -59.488800287246704, "max": 67.87539982795715, "count": 2616 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2032150691502715, "min": -0.33299006179252766, "max": 0.3775018179055416, "count": 2616 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -29.669400095939636, "min": -59.488800287246704, "max": 67.87539982795715, "count": 2616 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2616 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2616 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018825337445984285, "min": 0.010775110175988327, "max": 0.02479499242811774, "count": 1270 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018825337445984285, "min": 0.010775110175988327, "max": 0.02479499242811774, "count": 1270 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0716807467242082, "min": 0.06093314327299595, "max": 0.0890697586039702, "count": 1270 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0716807467242082, "min": 0.06093314327299595, "max": 0.0890697586039702, "count": 1270 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07204869166016578, "min": 0.06128497533500195, "max": 0.0895669976870219, "count": 1270 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07204869166016578, "min": 0.06128497533500195, "max": 0.0895669976870219, "count": 1270 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 8.539211730397e-05, "min": 8.539211730397e-05, "max": 0.000137631183184424, "count": 1270 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 8.539211730397e-05, "min": 8.539211730397e-05, "max": 0.000137631183184424, "count": 1270 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 1270 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 1270 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004275333396999999, "min": 0.004275333396999999, "max": 0.006884676042400002, "count": 1270 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004275333396999999, "min": 0.004275333396999999, "max": 0.006884676042400002, "count": 1270 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709507748", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/uoch/tf/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1709534942" }, "total": 27194.501877950002, "count": 1, "self": 0.08062203200097429, "children": { "run_training.setup": { "total": 0.013562335000017356, "count": 1, "self": 0.013562335000017356 }, "TrainerController.start_learning": { "total": 27194.407693583, "count": 1, "self": 19.885329335604183, "children": { "TrainerController._reset_env": { "total": 2.685746788013603, "count": 132, "self": 2.685746788013603 }, "TrainerController.advance": { "total": 27171.644558172382, "count": 1816540, "self": 20.538421145582106, "children": { "env_step": { "total": 18550.791161325982, "count": 1816540, "self": 13707.599330714493, "children": { "SubprocessEnvManager._take_step": { "total": 4830.228453776381, "count": 1816540, "self": 138.82647160194665, "children": { "TorchPolicy.evaluate": { "total": 4691.401982174434, "count": 3281539, "self": 4691.401982174434 } } }, "workers": { "total": 12.963376835108477, "count": 1816539, "self": 0.0, "children": { "worker_root": { "total": 27167.23741055864, "count": 1816539, "is_parallel": true, "self": 15947.144388470559, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002001161000009688, "count": 2, "is_parallel": true, "self": 0.0007302410000988857, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012709199999108023, "count": 8, "is_parallel": true, "self": 0.0012709199999108023 } } }, "UnityEnvironment.step": { "total": 0.016199861999950826, "count": 1, "is_parallel": true, "self": 0.0003734129999202196, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002923530000202845, "count": 1, "is_parallel": true, "self": 0.0002923530000202845 }, "communicator.exchange": { "total": 0.014475216999983331, "count": 1, "is_parallel": true, "self": 0.014475216999983331 }, "steps_from_proto": { "total": 0.001058879000026991, "count": 2, "is_parallel": true, "self": 0.0002293930000405453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008294859999864457, "count": 8, "is_parallel": true, "self": 0.0008294859999864457 } } } } } } }, "steps_from_proto": { "total": 0.13682280099931177, "count": 262, "is_parallel": true, "self": 0.026687844031130226, "children": { "_process_rank_one_or_two_observation": { "total": 0.11013495696818154, "count": 1048, "is_parallel": true, "self": 0.11013495696818154 } } }, "UnityEnvironment.step": { "total": 11219.95619928708, "count": 1816538, "is_parallel": true, "self": 588.137065331217, "children": { "UnityEnvironment._generate_step_input": { "total": 414.8245948215152, "count": 1816538, "is_parallel": true, "self": 414.8245948215152 }, "communicator.exchange": { "total": 8498.604662810401, "count": 1816538, "is_parallel": true, "self": 8498.604662810401 }, "steps_from_proto": { "total": 1718.3898763239472, "count": 3633076, "is_parallel": true, "self": 328.77084005874667, "children": { "_process_rank_one_or_two_observation": { "total": 1389.6190362652005, "count": 14532304, "is_parallel": true, "self": 1389.6190362652005 } } } } } } } } } } }, "trainer_advance": { "total": 8600.314975700818, "count": 1816539, "self": 172.27163687083157, "children": { "process_trajectory": { "total": 3106.2878394979552, "count": 1816539, "self": 3025.146080364957, "children": { "RLTrainer._checkpoint": { "total": 81.14175913299817, "count": 523, "self": 81.14175913299817 } } }, "_update_policy": { "total": 5321.755499332032, "count": 1270, "self": 2836.8128273619263, "children": { "TorchPOCAOptimizer.update": { "total": 2484.9426719701055, "count": 38100, "self": 2484.9426719701055 } } } } } } }, "trainer_threads": { "total": 1.152999175246805e-06, "count": 1, "self": 1.152999175246805e-06 }, "TrainerController._save_models": { "total": 0.19205813400185434, "count": 1, "self": 0.015921137000987073, "children": { "RLTrainer._checkpoint": { "total": 0.17613699700086727, "count": 1, "self": 0.17613699700086727 } } } } } } }