| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 2.5471396446228027, | |
| "min": 2.518519878387451, | |
| "max": 3.2957026958465576, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 53225.03125, | |
| "min": 26359.36328125, | |
| "max": 146059.90625, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 999.0, | |
| "min": 470.4, | |
| "max": 999.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19980.0, | |
| "min": 16052.0, | |
| "max": 23568.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1190.6581460972955, | |
| "min": 1187.8565262356556, | |
| "max": 1202.9911653894392, | |
| "count": 99 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 2381.316292194591, | |
| "min": 2375.713052471311, | |
| "max": 12010.04267761486, | |
| "count": 99 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 4999270.0, | |
| "min": 9590.0, | |
| "max": 4999270.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 4999270.0, | |
| "min": 9590.0, | |
| "max": 4999270.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 1.2714733657048782e-06, | |
| "min": -0.020758194848895073, | |
| "max": 0.07347887009382248, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 1.2714734111796133e-05, | |
| "min": -0.2474859654903412, | |
| "max": 1.1021467447280884, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 8.964687481238798e-07, | |
| "min": -0.01737458072602749, | |
| "max": 0.07347381860017776, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 8.96468736755196e-06, | |
| "min": -0.2468915432691574, | |
| "max": 1.102107286453247, | |
| "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": 0.0, | |
| "min": -0.6153846153846154, | |
| "max": 0.2584857131753649, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 0.0, | |
| "min": -8.0, | |
| "max": 3.6187999844551086, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": -0.6153846153846154, | |
| "max": 0.2584857131753649, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": -8.0, | |
| "max": 3.6187999844551086, | |
| "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": 0.0137361578126729, | |
| "min": 0.01036202953546308, | |
| "max": 0.02374208786059171, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.0137361578126729, | |
| "min": 0.01036202953546308, | |
| "max": 0.02374208786059171, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 3.0206498413676286e-10, | |
| "min": 2.1270849942522928e-10, | |
| "max": 0.004814230355744561, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 3.0206498413676286e-10, | |
| "min": 2.1270849942522928e-10, | |
| "max": 0.004814230355744561, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 3.0796516771921155e-10, | |
| "min": 2.3463272436075046e-10, | |
| "max": 0.0048274338866273565, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 3.0796516771921155e-10, | |
| "min": 2.3463272436075046e-10, | |
| "max": 0.0048274338866273565, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 229 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 229 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1723531261", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --force", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.4.0+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1723536521" | |
| }, | |
| "total": 5259.733144883998, | |
| "count": 1, | |
| "self": 0.21879728099702334, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.015174002001003828, | |
| "count": 1, | |
| "self": 0.015174002001003828 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 5259.499173601, | |
| "count": 1, | |
| "self": 5.810825854159702, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 5.329037338000489, | |
| "count": 25, | |
| "self": 5.329037338000489 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 5248.2661043158405, | |
| "count": 326422, | |
| "self": 6.435424847264585, | |
| "children": { | |
| "env_step": { | |
| "total": 4027.7808730130964, | |
| "count": 326422, | |
| "self": 2953.620851730382, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1070.5567355640997, | |
| "count": 326422, | |
| "self": 33.74965573751979, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1036.8070798265799, | |
| "count": 647932, | |
| "self": 1036.8070798265799 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 3.603285718614643, | |
| "count": 326422, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 5251.711907004828, | |
| "count": 326422, | |
| "is_parallel": true, | |
| "self": 2891.7489755443694, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0016552800007048063, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0004318839983170619, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012233960023877444, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012233960023877444 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.016775609999967855, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003588440013118088, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00030647700077679474, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00030647700077679474 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.015066494999700808, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.015066494999700808 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0010437939981784439, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00021380399630288593, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0008299900018755579, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0008299900018755579 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 2359.9388709144587, | |
| "count": 326421, | |
| "is_parallel": true, | |
| "self": 117.36705112984964, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 80.85787603428253, | |
| "count": 326421, | |
| "is_parallel": true, | |
| "self": 80.85787603428253 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1819.6714675248859, | |
| "count": 326421, | |
| "is_parallel": true, | |
| "self": 1819.6714675248859 | |
| }, | |
| "steps_from_proto": { | |
| "total": 342.0424762254406, | |
| "count": 652842, | |
| "is_parallel": true, | |
| "self": 65.64000596241021, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 276.4024702630304, | |
| "count": 2611368, | |
| "is_parallel": true, | |
| "self": 276.4024702630304 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.02406054600032803, | |
| "count": 48, | |
| "is_parallel": true, | |
| "self": 0.004670860997066484, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.019389685003261548, | |
| "count": 192, | |
| "is_parallel": true, | |
| "self": 0.019389685003261548 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1214.0498064554795, | |
| "count": 326422, | |
| "self": 47.84008903884569, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 291.8457330606252, | |
| "count": 326422, | |
| "self": 290.8571599916213, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.9885730690039054, | |
| "count": 10, | |
| "self": 0.9885730690039054 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 874.3639843560086, | |
| "count": 229, | |
| "self": 419.8367884019681, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 454.5271959540405, | |
| "count": 6876, | |
| "self": 454.5271959540405 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.439986464101821e-07, | |
| "count": 1, | |
| "self": 6.439986464101821e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.0932054490003793, | |
| "count": 1, | |
| "self": 0.0010181920006289147, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09218725699975039, | |
| "count": 1, | |
| "self": 0.09218725699975039 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |