{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.28106951713562, "min": 2.267874240875244, "max": 3.2957401275634766, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43942.5234375, "min": 7168.041015625, "max": 121777.65625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 43.283185840707965, "min": 43.283185840707965, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19564.0, "min": 3996.0, "max": 29644.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1520.9714079208918, "min": 1190.1934564205515, "max": 1528.6711023492037, "count": 432 }, "SoccerTwos.Self-play.ELO.sum": { "value": 343739.53819012153, "min": 2380.386912841103, "max": 343739.53819012153, "count": 432 }, "SoccerTwos.Step.mean": { "value": 4999978.0, "min": 9610.0, "max": 4999978.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999978.0, "min": 9610.0, "max": 4999978.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.09605994075536728, "min": -0.044944796711206436, "max": 0.24079547822475433, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 21.613487243652344, "min": -7.415891647338867, "max": 28.896575927734375, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09307499974966049, "min": -0.0555872842669487, "max": 0.2406833916902542, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 20.941875457763672, "min": -9.17190170288086, "max": 28.5579833984375, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.12103555705812243, "min": -0.7142857142857143, "max": 0.5604533327950372, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 27.233000338077545, "min": -31.924399971961975, "max": 62.52079999446869, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.12103555705812243, "min": -0.7142857142857143, "max": 0.5604533327950372, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 27.233000338077545, "min": -31.924399971961975, "max": 62.52079999446869, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01370433546132214, "min": 0.010159113164021013, "max": 0.02330286295618862, "count": 235 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01370433546132214, "min": 0.010159113164021013, "max": 0.02330286295618862, "count": 235 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10285864472389221, "min": 3.843776156031709e-07, "max": 0.11228427737951278, "count": 235 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10285864472389221, "min": 3.843776156031709e-07, "max": 0.11228427737951278, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1059309276441733, "min": 5.53159195722704e-07, "max": 0.11651800498366356, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1059309276441733, "min": 5.53159195722704e-07, "max": 0.11651800498366356, "count": 235 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 235 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 235 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710950733", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/sagravela/miniconda3/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos --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": "1710963370" }, "total": 12637.017107801, "count": 1, "self": 0.2702826009990531, "children": { "run_training.setup": { "total": 0.010760700000901124, "count": 1, "self": 0.010760700000901124 }, "TrainerController.start_learning": { "total": 12636.7360645, "count": 1, "self": 7.7868017927921755, "children": { "TrainerController._reset_env": { "total": 2.9091304129997297, "count": 25, "self": 2.9091304129997297 }, "TrainerController.advance": { "total": 12625.814257293205, "count": 329846, "self": 8.441290810438659, "children": { "env_step": { "total": 9973.540340834876, "count": 329846, "self": 6361.316283252472, "children": { "SubprocessEnvManager._take_step": { "total": 3607.298174093472, "count": 329846, "self": 62.541471448903394, "children": { "TorchPolicy.evaluate": { "total": 3544.7567026445686, "count": 640110, "self": 3544.7567026445686 } } }, "workers": { "total": 4.925883488931504, "count": 329846, "self": 0.0, "children": { "worker_root": { "total": 12619.719503792963, "count": 329846, "is_parallel": true, "self": 7178.251303920337, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020968999997421633, "count": 2, "is_parallel": true, "self": 0.0005801999977848027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015167000019573607, "count": 8, "is_parallel": true, "self": 0.0015167000019573607 } } }, "UnityEnvironment.step": { "total": 0.023598699999638484, "count": 1, "is_parallel": true, "self": 0.0004140999990340788, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033260000054724514, "count": 1, "is_parallel": true, "self": 0.00033260000054724514 }, "communicator.exchange": { "total": 0.02134190000106173, "count": 1, "is_parallel": true, "self": 0.02134190000106173 }, "steps_from_proto": { "total": 0.001510099998995429, "count": 2, "is_parallel": true, "self": 0.00035909999678551685, "children": { "_process_rank_one_or_two_observation": { "total": 0.001151000002209912, "count": 8, "is_parallel": true, "self": 0.001151000002209912 } } } } } } }, "UnityEnvironment.step": { "total": 5441.424514472648, "count": 329845, "is_parallel": true, "self": 179.02451860147812, "children": { "UnityEnvironment._generate_step_input": { "total": 130.18842834278075, "count": 329845, "is_parallel": true, "self": 130.18842834278075 }, "communicator.exchange": { "total": 4501.183542639677, "count": 329845, "is_parallel": true, "self": 4501.183542639677 }, "steps_from_proto": { "total": 631.028024888712, "count": 659690, "is_parallel": true, "self": 141.31926914761425, "children": { "_process_rank_one_or_two_observation": { "total": 489.7087557410978, "count": 2638760, "is_parallel": true, "self": 489.7087557410978 } } } } }, "steps_from_proto": { "total": 0.04368539997813059, "count": 48, "is_parallel": true, "self": 0.0100143999698048, "children": { "_process_rank_one_or_two_observation": { "total": 0.03367100000832579, "count": 192, "is_parallel": true, "self": 0.03367100000832579 } } } } } } } } }, "trainer_advance": { "total": 2643.8326256478904, "count": 329846, "self": 60.531306319691794, "children": { "process_trajectory": { "total": 919.1341488831968, "count": 329846, "self": 916.7031596771958, "children": { "RLTrainer._checkpoint": { "total": 2.430989206000959, "count": 10, "self": 2.430989206000959 } } }, "_update_policy": { "total": 1664.1671704450018, "count": 235, "self": 739.3315952770809, "children": { "TorchPOCAOptimizer.update": { "total": 924.835575167921, "count": 7062, "self": 924.835575167921 } } } } } } }, "trainer_threads": { "total": 8.00002453615889e-07, "count": 1, "self": 8.00002453615889e-07 }, "TrainerController._save_models": { "total": 0.22587420100171585, "count": 1, "self": 0.0014189000030455645, "children": { "RLTrainer._checkpoint": { "total": 0.22445530099867028, "count": 1, "self": 0.22445530099867028 } } } } } } }