| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.5260498523712158, | |
| "min": 1.47836434841156, | |
| "max": 1.5717905759811401, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 30472.1640625, | |
| "min": 23978.40234375, | |
| "max": 38699.16796875, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 70.20289855072464, | |
| "min": 58.97560975609756, | |
| "max": 111.08695652173913, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19376.0, | |
| "min": 14248.0, | |
| "max": 21124.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1712.0493582103122, | |
| "min": 1700.9733828056937, | |
| "max": 1764.6453188312037, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 236262.81143302307, | |
| "min": 135199.9946404582, | |
| "max": 293076.2351296764, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 29999974.0, | |
| "min": 27709981.0, | |
| "max": 29999974.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 29999974.0, | |
| "min": 27709981.0, | |
| "max": 29999974.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.02527669444680214, | |
| "min": -0.12162230163812637, | |
| "max": 0.04789558798074722, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -3.513460636138916, | |
| "min": -18.121723175048828, | |
| "max": 7.892575263977051, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.02623376064002514, | |
| "min": -0.12381523102521896, | |
| "max": 0.050768427550792694, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -3.6464927196502686, | |
| "min": -18.448469161987305, | |
| "max": 8.272490501403809, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.09223597041136927, | |
| "min": -0.3490041961203088, | |
| "max": 0.36174961674304407, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 12.820799887180328, | |
| "min": -49.90760004520416, | |
| "max": 47.389199793338776, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.09223597041136927, | |
| "min": -0.3490041961203088, | |
| "max": 0.36174961674304407, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 12.820799887180328, | |
| "min": -49.90760004520416, | |
| "max": 47.389199793338776, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 230 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01872896176064387, | |
| "min": 0.012019599394019071, | |
| "max": 0.024193876256079723, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01872896176064387, | |
| "min": 0.012019599394019071, | |
| "max": 0.024193876256079723, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.09518186748027802, | |
| "min": 0.0706393318871657, | |
| "max": 0.09518186748027802, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.09518186748027802, | |
| "min": 0.0706393318871657, | |
| "max": 0.09518186748027802, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.09562629113594691, | |
| "min": 0.07152016038695971, | |
| "max": 0.09562629113594691, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.09562629113594691, | |
| "min": 0.07152016038695971, | |
| "max": 0.09562629113594691, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 111 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 111 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1747997676", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/misbah/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.7.0+cu126", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1748003870" | |
| }, | |
| "total": 6193.243015332002, | |
| "count": 1, | |
| "self": 0.2190838940005051, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.008608447009464726, | |
| "count": 1, | |
| "self": 0.008608447009464726 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 6193.015322990992, | |
| "count": 1, | |
| "self": 2.8038882425171323, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.4619750839920016, | |
| "count": 13, | |
| "self": 1.4619750839920016 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 6188.660720257481, | |
| "count": 155986, | |
| "self": 2.6640657623356674, | |
| "children": { | |
| "env_step": { | |
| "total": 1907.5624348415295, | |
| "count": 155986, | |
| "self": 1611.387107489776, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 294.368761390273, | |
| "count": 155986, | |
| "self": 14.094670786944334, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 280.27409060332866, | |
| "count": 288798, | |
| "self": 280.27409060332866 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 1.8065659614803735, | |
| "count": 155986, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 6188.076122690254, | |
| "count": 155986, | |
| "is_parallel": true, | |
| "self": 4824.377654081254, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0013928839907748625, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.000349724039551802, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0010431599512230605, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0010431599512230605 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.014681180997285992, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00035585599835030735, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0002818450011545792, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002818450011545792 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.013071444001980126, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.013071444001980126 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0009720359958009794, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0001990060118259862, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007730299839749932, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007730299839749932 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.014256768015911803, | |
| "count": 24, | |
| "is_parallel": true, | |
| "self": 0.002820325084030628, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.011436442931881174, | |
| "count": 96, | |
| "is_parallel": true, | |
| "self": 0.011436442931881174 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1363.684211840984, | |
| "count": 155985, | |
| "is_parallel": true, | |
| "self": 67.68927301358781, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 75.72199507434561, | |
| "count": 155985, | |
| "is_parallel": true, | |
| "self": 75.72199507434561 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1002.7482204776024, | |
| "count": 155985, | |
| "is_parallel": true, | |
| "self": 1002.7482204776024 | |
| }, | |
| "steps_from_proto": { | |
| "total": 217.5247232754482, | |
| "count": 311970, | |
| "is_parallel": true, | |
| "self": 46.355050702157314, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 171.16967257329088, | |
| "count": 1247880, | |
| "is_parallel": true, | |
| "self": 171.16967257329088 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 4278.434219653616, | |
| "count": 155986, | |
| "self": 18.51109605266538, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 281.2572263569018, | |
| "count": 155986, | |
| "self": 280.7852156188892, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.47201073801261373, | |
| "count": 5, | |
| "self": 0.47201073801261373 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 3978.665897244049, | |
| "count": 111, | |
| "self": 154.19840713523445, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 3824.4674901088147, | |
| "count": 3330, | |
| "self": 3824.4674901088147 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 5.970068741589785e-07, | |
| "count": 1, | |
| "self": 5.970068741589785e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08873880999453831, | |
| "count": 1, | |
| "self": 0.0013925339881097898, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.08734627600642852, | |
| "count": 1, | |
| "self": 0.08734627600642852 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |