{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7498799562454224, "min": 1.592118263244629, "max": 3.2957546710968018, "count": 1307 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36901.46875, "min": 25812.775390625, "max": 126791.1015625, "count": 1307 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.21111111111111, "min": 41.440677966101696, "max": 999.0, "count": 1307 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19876.0, "min": 16224.0, "max": 23540.0, "count": 1307 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1606.2163802212315, "min": 1182.7654606491549, "max": 1621.595618087904, "count": 1285 }, "SoccerTwos.Self-play.ELO.sum": { "value": 289118.94843982166, "min": 2367.04618318775, "max": 366638.36362125515, "count": 1285 }, "SoccerTwos.Step.mean": { "value": 13069962.0, "min": 9740.0, "max": 13069962.0, "count": 1307 }, "SoccerTwos.Step.sum": { "value": 13069962.0, "min": 9740.0, "max": 13069962.0, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004954230971634388, "min": -0.13620899617671967, "max": 0.1899797022342682, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.8917615413665771, "min": -24.108993530273438, "max": 29.62128448486328, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0023781233467161655, "min": -0.13830557465553284, "max": 0.19220112264156342, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.42806220054626465, "min": -24.480087280273438, "max": 28.44996452331543, "count": 1307 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1307 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.15848222043779162, "min": -0.5208800000449022, "max": 0.6031836733526114, "count": 1307 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -28.52679967880249, "min": -56.21600031852722, "max": 59.11199998855591, "count": 1307 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.15848222043779162, "min": -0.5208800000449022, "max": 0.6031836733526114, "count": 1307 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -28.52679967880249, "min": -56.21600031852722, "max": 59.11199998855591, "count": 1307 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1307 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1307 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01879232389231523, "min": 0.010547318649090205, "max": 0.023986967280507088, "count": 632 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01879232389231523, "min": 0.010547318649090205, "max": 0.023986967280507088, "count": 632 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09966869627436002, "min": 3.370774584254832e-05, "max": 0.129342669993639, "count": 632 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09966869627436002, "min": 3.370774584254832e-05, "max": 0.129342669993639, "count": 632 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10174222042163213, "min": 3.300160739551454e-05, "max": 0.13165664548675218, "count": 632 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10174222042163213, "min": 3.300160739551454e-05, "max": 0.13165664548675218, "count": 632 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 632 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 632 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 632 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 632 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 632 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 632 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682865484", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ntrant/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --resume --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+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1682877156" }, "total": 11671.585723015945, "count": 1, "self": 0.04175698268227279, "children": { "run_training.setup": { "total": 0.014840701129287481, "count": 1, "self": 0.014840701129287481 }, "TrainerController.start_learning": { "total": 11671.529125332134, "count": 1, "self": 8.791507692774758, "children": { "TrainerController._reset_env": { "total": 3.884134766412899, "count": 66, "self": 3.884134766412899 }, "TrainerController.advance": { "total": 11658.727227292024, "count": 899092, "self": 8.92384381708689, "children": { "env_step": { "total": 8612.462243863149, "count": 899092, "self": 6386.267457857262, "children": { "SubprocessEnvManager._take_step": { "total": 2220.4036682059523, "count": 899092, "self": 58.96731872973032, "children": { "TorchPolicy.evaluate": { "total": 2161.436349476222, "count": 1645541, "self": 2161.436349476222 } } }, "workers": { "total": 5.791117799934, "count": 899091, "self": 0.0, "children": { "worker_root": { "total": 11657.65445263614, "count": 899091, "is_parallel": true, "self": 6380.174212039448, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002009287942200899, "count": 2, "is_parallel": true, "self": 0.0004376454744488001, "children": { "_process_rank_one_or_two_observation": { "total": 0.001571642467752099, "count": 8, "is_parallel": true, "self": 0.001571642467752099 } } }, "UnityEnvironment.step": { "total": 0.017400535056367517, "count": 1, "is_parallel": true, "self": 0.00042957509867846966, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003150850534439087, "count": 1, "is_parallel": true, "self": 0.0003150850534439087 }, "communicator.exchange": { "total": 0.015351725975051522, "count": 1, "is_parallel": true, "self": 0.015351725975051522 }, "steps_from_proto": { "total": 0.001304148929193616, "count": 2, "is_parallel": true, "self": 0.00030725402757525444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009968949016183615, "count": 8, "is_parallel": true, "self": 0.0009968949016183615 } } } } } } }, "UnityEnvironment.step": { "total": 5277.375927911606, "count": 899090, "is_parallel": true, "self": 353.8368307100609, "children": { "UnityEnvironment._generate_step_input": { "total": 216.4185826391913, "count": 899090, "is_parallel": true, "self": 216.4185826391913 }, "communicator.exchange": { "total": 3690.090112598613, "count": 899090, "is_parallel": true, "self": 3690.090112598613 }, "steps_from_proto": { "total": 1017.0304019637406, "count": 1798180, "is_parallel": true, "self": 186.7083051521331, "children": { "_process_rank_one_or_two_observation": { "total": 830.3220968116075, "count": 7192720, "is_parallel": true, "self": 830.3220968116075 } } } } }, "steps_from_proto": { "total": 0.10431268508546054, "count": 130, "is_parallel": true, "self": 0.019125621300190687, "children": { "_process_rank_one_or_two_observation": { "total": 0.08518706378526986, "count": 520, "is_parallel": true, "self": 0.08518706378526986 } } } } } } } } }, "trainer_advance": { "total": 3037.341139611788, "count": 899091, "self": 75.78526360704564, "children": { "process_trajectory": { "total": 1247.6466317374725, "count": 899091, "self": 1244.4682482234202, "children": { "RLTrainer._checkpoint": { "total": 3.178383514052257, "count": 26, "self": 3.178383514052257 } } }, "_update_policy": { "total": 1713.90924426727, "count": 632, "self": 1164.2530386459548, "children": { "TorchPOCAOptimizer.update": { "total": 549.6562056213152, "count": 18960, "self": 549.6562056213152 } } } } } } }, "trainer_threads": { "total": 5.799811333417892e-07, "count": 1, "self": 5.799811333417892e-07 }, "TrainerController._save_models": { "total": 0.12625500094145536, "count": 1, "self": 0.0014630958903580904, "children": { "RLTrainer._checkpoint": { "total": 0.12479190505109727, "count": 1, "self": 0.12479190505109727 } } } } } } }