| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.9624570608139038, | |
| "min": 1.923630952835083, | |
| "max": 3.2957539558410645, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 37867.5703125, | |
| "min": 23951.3359375, | |
| "max": 111470.4765625, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 55.449438202247194, | |
| "min": 42.19827586206897, | |
| "max": 999.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19740.0, | |
| "min": 13844.0, | |
| "max": 26936.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1554.946312420408, | |
| "min": 1201.9231675482797, | |
| "max": 1587.1992546538252, | |
| "count": 497 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 276780.4436108326, | |
| "min": 2403.8463350965594, | |
| "max": 363101.54652551236, | |
| "count": 497 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 4999892.0, | |
| "min": 9484.0, | |
| "max": 4999892.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 4999892.0, | |
| "min": 9484.0, | |
| "max": 4999892.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.008518635295331478, | |
| "min": -0.10306870192289352, | |
| "max": 0.1407080590724945, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -1.507798433303833, | |
| "min": -19.170778274536133, | |
| "max": 22.501344680786133, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0071655274368822575, | |
| "min": -0.09862442314624786, | |
| "max": 0.13518813252449036, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -1.2682983875274658, | |
| "min": -18.34414291381836, | |
| "max": 22.57685089111328, | |
| "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": 0.06365536700534281, | |
| "min": -0.6143529384451754, | |
| "max": 0.6472571460264069, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 11.266999959945679, | |
| "min": -69.41000020503998, | |
| "max": 43.75999963283539, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.06365536700534281, | |
| "min": -0.6143529384451754, | |
| "max": 0.6472571460264069, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 11.266999959945679, | |
| "min": -69.41000020503998, | |
| "max": 43.75999963283539, | |
| "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": 0.01893478469767918, | |
| "min": 0.0111278524416169, | |
| "max": 0.02454151203855872, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01893478469767918, | |
| "min": 0.0111278524416169, | |
| "max": 0.02454151203855872, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.10860741411646208, | |
| "min": 4.050080739640786e-05, | |
| "max": 0.11947573646903038, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.10860741411646208, | |
| "min": 4.050080739640786e-05, | |
| "max": 0.11947573646903038, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.11060767670472463, | |
| "min": 3.884270427079173e-05, | |
| "max": 0.12212536409497261, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.11060767670472463, | |
| "min": 3.884270427079173e-05, | |
| "max": 0.12212536409497261, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 241 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 241 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1737452707", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/hwting/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", | |
| "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": "1737458723" | |
| }, | |
| "total": 6016.564443802999, | |
| "count": 1, | |
| "self": 0.21819680599946878, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.01773842200054787, | |
| "count": 1, | |
| "self": 0.01773842200054787 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 6016.328508574999, | |
| "count": 1, | |
| "self": 5.853945008540904, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.3960548999966704, | |
| "count": 25, | |
| "self": 2.3960548999966704 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 6007.954160431462, | |
| "count": 340918, | |
| "self": 5.2438944181958504, | |
| "children": { | |
| "env_step": { | |
| "total": 4626.849999205202, | |
| "count": 340918, | |
| "self": 3270.4301313490214, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1352.722741669084, | |
| "count": 340918, | |
| "self": 29.190269605238427, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1323.5324720638455, | |
| "count": 630616, | |
| "self": 1323.5324720638455 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 3.6971261870967282, | |
| "count": 340918, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 6009.020171433953, | |
| "count": 340918, | |
| "is_parallel": true, | |
| "self": 3405.0127552547638, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.00157080099961604, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0004186269979982171, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0011521740016178228, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0011521740016178228 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.016684693000570405, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006452709967561532, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005203280015848577, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005203280015848577 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.014446198001678567, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.014446198001678567 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001072896000550827, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00022127800548332743, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0008516179950674996, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0008516179950674996 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 2603.976741327191, | |
| "count": 340917, | |
| "is_parallel": true, | |
| "self": 165.08438993543677, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 148.05314765239018, | |
| "count": 340917, | |
| "is_parallel": true, | |
| "self": 148.05314765239018 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1887.838500383772, | |
| "count": 340917, | |
| "is_parallel": true, | |
| "self": 1887.838500383772 | |
| }, | |
| "steps_from_proto": { | |
| "total": 403.0007033555921, | |
| "count": 681834, | |
| "is_parallel": true, | |
| "self": 74.92860740868491, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 328.0720959469072, | |
| "count": 2727336, | |
| "is_parallel": true, | |
| "self": 328.0720959469072 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.030674851997900987, | |
| "count": 48, | |
| "is_parallel": true, | |
| "self": 0.005504211989318719, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.025170640008582268, | |
| "count": 192, | |
| "is_parallel": true, | |
| "self": 0.025170640008582268 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1375.860266808064, | |
| "count": 340918, | |
| "self": 44.38020454633079, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 630.5366703117506, | |
| "count": 340918, | |
| "self": 629.3090538527431, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.2276164590075496, | |
| "count": 10, | |
| "self": 1.2276164590075496 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 700.9433919499825, | |
| "count": 241, | |
| "self": 406.35289914812165, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 294.5904928018608, | |
| "count": 7230, | |
| "self": 294.5904928018608 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 5.809997674077749e-07, | |
| "count": 1, | |
| "self": 5.809997674077749e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.12434765400030301, | |
| "count": 1, | |
| "self": 0.0013083249978080858, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.12303932900249492, | |
| "count": 1, | |
| "self": 0.12303932900249492 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |