| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.671779990196228, | |
| "min": 1.483157753944397, | |
| "max": 3.29573392868042, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 33328.60546875, | |
| "min": 21977.736328125, | |
| "max": 113948.734375, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 60.44578313253012, | |
| "min": 40.98360655737705, | |
| "max": 999.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 20068.0, | |
| "min": 7992.0, | |
| "max": 30456.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1539.0438597037996, | |
| "min": 1201.7416295213911, | |
| "max": 1632.7729248992605, | |
| "count": 2169 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 255481.28071083073, | |
| "min": 2407.9198778528084, | |
| "max": 393499.67341582046, | |
| "count": 2169 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 21719990.0, | |
| "min": 9976.0, | |
| "max": 21719990.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 21719990.0, | |
| "min": 9976.0, | |
| "max": 21719990.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.0039015451911836863, | |
| "min": -0.16042177379131317, | |
| "max": 0.18803301453590393, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.6437549591064453, | |
| "min": -29.35718536376953, | |
| "max": 25.85744285583496, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0019325704779475927, | |
| "min": -0.16366998851299286, | |
| "max": 0.18803183734416962, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.3188741207122803, | |
| "min": -29.809600830078125, | |
| "max": 24.820201873779297, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.049229092308969206, | |
| "min": -0.615013333161672, | |
| "max": 0.49932221902741325, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 8.12280023097992, | |
| "min": -58.684799790382385, | |
| "max": 63.74240005016327, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.049229092308969206, | |
| "min": -0.615013333161672, | |
| "max": 0.49932221902741325, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 8.12280023097992, | |
| "min": -58.684799790382385, | |
| "max": 63.74240005016327, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 2172 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.013729617009327436, | |
| "min": 0.010989157442721383, | |
| "max": 0.025509973475709557, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.013729617009327436, | |
| "min": 0.010989157442721383, | |
| "max": 0.025509973475709557, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.1058132159213225, | |
| "min": 0.0009146183729171753, | |
| "max": 0.1211084894835949, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.1058132159213225, | |
| "min": 0.0009146183729171753, | |
| "max": 0.1211084894835949, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.10755141600966453, | |
| "min": 0.0009252421053436896, | |
| "max": 0.12316837261120478, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.10755141600966453, | |
| "min": 0.0009252421053436896, | |
| "max": 0.12316837261120478, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 1052 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 1052 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1736415869", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/stefan/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos2 --no-graphics --torch-device cuda", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.5.1+cu124", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1736451844" | |
| }, | |
| "total": 35974.67269840401, | |
| "count": 1, | |
| "self": 0.40740082100819563, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.010543634001805913, | |
| "count": 1, | |
| "self": 0.010543634001805913 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 35974.254753949, | |
| "count": 1, | |
| "self": 20.7283982641311, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.7039670909798588, | |
| "count": 109, | |
| "self": 2.7039670909798588 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 35950.661532302875, | |
| "count": 1498144, | |
| "self": 19.332999862155702, | |
| "children": { | |
| "env_step": { | |
| "total": 27302.5172698968, | |
| "count": 1498144, | |
| "self": 16589.43508921757, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 10700.206373095512, | |
| "count": 1498144, | |
| "self": 123.36394279388333, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 10576.842430301629, | |
| "count": 2730560, | |
| "self": 10576.842430301629 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 12.875807583717688, | |
| "count": 1498143, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 35929.36511270509, | |
| "count": 1498143, | |
| "is_parallel": true, | |
| "self": 21602.363495709753, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0017083109996747226, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0005188049835851416, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001189506016089581, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001189506016089581 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.02624909100268269, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00038735600537620485, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00039570599619764835, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00039570599619764835 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.024261833001219202, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.024261833001219202 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0012041959998896345, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0002781369985314086, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0009260590013582259, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0009260590013582259 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 14326.880298964265, | |
| "count": 1498142, | |
| "is_parallel": true, | |
| "self": 481.7784100755889, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 320.9030825123482, | |
| "count": 1498142, | |
| "is_parallel": true, | |
| "self": 320.9030825123482 | |
| }, | |
| "communicator.exchange": { | |
| "total": 12007.851514953283, | |
| "count": 1498142, | |
| "is_parallel": true, | |
| "self": 12007.851514953283 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1516.3472914230442, | |
| "count": 2996284, | |
| "is_parallel": true, | |
| "self": 327.8235669827118, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1188.5237244403324, | |
| "count": 11985136, | |
| "is_parallel": true, | |
| "self": 1188.5237244403324 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.12131803107331507, | |
| "count": 216, | |
| "is_parallel": true, | |
| "self": 0.026903044199571013, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.09441498687374406, | |
| "count": 864, | |
| "is_parallel": true, | |
| "self": 0.09441498687374406 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 8628.811262543917, | |
| "count": 1498143, | |
| "self": 161.23468632528238, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 5099.0348406058765, | |
| "count": 1498143, | |
| "self": 5092.362769061881, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 6.672071543995116, | |
| "count": 43, | |
| "self": 6.672071543995116 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 3368.541735612758, | |
| "count": 1052, | |
| "self": 1602.0031282262353, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 1766.538607386523, | |
| "count": 31569, | |
| "self": 1766.538607386523 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 7.300113793462515e-07, | |
| "count": 1, | |
| "self": 7.300113793462515e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.16085556100006215, | |
| "count": 1, | |
| "self": 0.001240865996805951, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.1596146950032562, | |
| "count": 1, | |
| "self": 0.1596146950032562 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |