| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.273122549057007, | |
| "min": 3.273122549057007, | |
| "max": 3.2956995964050293, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 88819.453125, | |
| "min": 36824.328125, | |
| "max": 105462.390625, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 986.3333333333334, | |
| "min": 349.0, | |
| "max": 999.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 23672.0, | |
| "min": 1396.0, | |
| "max": 31968.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1198.320921595067, | |
| "min": 1197.273575898641, | |
| "max": 1199.3173316810933, | |
| "count": 6 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 4793.283686380268, | |
| "min": 2394.547151797282, | |
| "max": 14377.498515805344, | |
| "count": 6 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 69978.0, | |
| "min": 9354.0, | |
| "max": 69978.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 69978.0, | |
| "min": 9354.0, | |
| "max": 69978.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.029395604506134987, | |
| "min": -0.029395604506134987, | |
| "max": -0.027391143143177032, | |
| "count": 5 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.4703296720981598, | |
| "min": -0.4703296720981598, | |
| "max": -0.27665016055107117, | |
| "count": 5 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.027215536683797836, | |
| "min": -0.027613306418061256, | |
| "max": -0.025287168100476265, | |
| "count": 5 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.4354485869407654, | |
| "min": -0.4354485869407654, | |
| "max": -0.2761234641075134, | |
| "count": 5 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.08109090544960716, | |
| "min": -0.38461538461538464, | |
| "max": 0.3400000110268593, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -0.8919999599456787, | |
| "min": -5.045199990272522, | |
| "max": 5.4400001764297485, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.08109090544960716, | |
| "min": -0.38461538461538464, | |
| "max": 0.3400000110268593, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -0.8919999599456787, | |
| "min": -5.045199990272522, | |
| "max": 5.4400001764297485, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 7 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.020737362704433812, | |
| "min": 0.019029662696647437, | |
| "max": 0.020737362704433812, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.020737362704433812, | |
| "min": 0.019029662696647437, | |
| "max": 0.020737362704433812, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0020418568774836048, | |
| "min": 0.0020418568774836048, | |
| "max": 0.0020418568774836048, | |
| "count": 1 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0020418568774836048, | |
| "min": 0.0020418568774836048, | |
| "max": 0.0020418568774836048, | |
| "count": 1 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.001893633756221139, | |
| "min": 0.001893633756221139, | |
| "max": 0.001893633756221139, | |
| "count": 1 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.001893633756221139, | |
| "min": 0.001893633756221139, | |
| "max": 0.001893633756221139, | |
| "count": 1 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 2 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 2 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1740688151", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", | |
| "command_line_arguments": "/Users/amir/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": "2.6.0", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1740688431" | |
| }, | |
| "total": 280.2057829590012, | |
| "count": 1, | |
| "self": 0.224106584002584, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.022819750000053318, | |
| "count": 1, | |
| "self": 0.022819750000053318 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 279.9588566249986, | |
| "count": 1, | |
| "self": 0.0579930067397072, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.7447732920009003, | |
| "count": 1, | |
| "self": 3.7447732920009003 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 276.02421032625716, | |
| "count": 5001, | |
| "self": 0.053040216935187345, | |
| "children": { | |
| "env_step": { | |
| "total": 225.45828245407756, | |
| "count": 5001, | |
| "self": 215.46659168500264, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 9.953332595054235, | |
| "count": 5001, | |
| "self": 0.24310704026720487, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 9.71022555478703, | |
| "count": 9958, | |
| "self": 9.71022555478703 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.03835817402068642, | |
| "count": 5000, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 276.7622806810941, | |
| "count": 5000, | |
| "is_parallel": true, | |
| "self": 69.43057033927471, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.001644916002987884, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0002262499947391916, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0014186660082486924, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0014186660082486924 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 207.33006542581643, | |
| "count": 5000, | |
| "is_parallel": true, | |
| "self": 0.6085860606945062, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 3.5735817189524823, | |
| "count": 5000, | |
| "is_parallel": true, | |
| "self": 3.5735817189524823 | |
| }, | |
| "communicator.exchange": { | |
| "total": 195.70611232615192, | |
| "count": 5000, | |
| "is_parallel": true, | |
| "self": 195.70611232615192 | |
| }, | |
| "steps_from_proto": { | |
| "total": 7.441785320017516, | |
| "count": 10000, | |
| "is_parallel": true, | |
| "self": 0.8515734473185148, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 6.590211872699001, | |
| "count": 40000, | |
| "is_parallel": true, | |
| "self": 6.590211872699001 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 50.51288765524441, | |
| "count": 5000, | |
| "self": 0.45996707937592873, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 7.4487364088709, | |
| "count": 5000, | |
| "self": 7.4487364088709 | |
| }, | |
| "_update_policy": { | |
| "total": 42.604184166997584, | |
| "count": 3, | |
| "self": 4.489408828998421, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 38.11477533799916, | |
| "count": 102, | |
| "self": 38.11477533799916 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.13188000000081956, | |
| "count": 1, | |
| "self": 2.0459003280848265e-05, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.13185954099753872, | |
| "count": 1, | |
| "self": 0.13185954099753872 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |