| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.7886731624603271, | |
| "min": 1.7538719177246094, | |
| "max": 3.2957756519317627, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 35029.375, | |
| "min": 10724.03515625, | |
| "max": 122329.875, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 43.990990990990994, | |
| "min": 39.483870967741936, | |
| "max": 999.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19532.0, | |
| "min": 2108.0, | |
| "max": 29424.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1473.0525575233607, | |
| "min": 1188.2391535706788, | |
| "max": 1502.293441927133, | |
| "count": 569 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 327017.6677701861, | |
| "min": 2376.4783071413576, | |
| "max": 362074.8879020111, | |
| "count": 569 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 6089982.0, | |
| "min": 9728.0, | |
| "max": 6089982.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 6089982.0, | |
| "min": 9728.0, | |
| "max": 6089982.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.050350673496723175, | |
| "min": -0.1030958890914917, | |
| "max": 0.18944373726844788, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -11.177849769592285, | |
| "min": -18.28963851928711, | |
| "max": 29.809932708740234, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.04108668491244316, | |
| "min": -0.10463780909776688, | |
| "max": 0.19806651771068573, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -9.121244430541992, | |
| "min": -18.162994384765625, | |
| "max": 29.94745635986328, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.08414774757247788, | |
| "min": -0.625, | |
| "max": 0.6562424284039121, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -18.680799961090088, | |
| "min": -64.89040005207062, | |
| "max": 53.10900020599365, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.08414774757247788, | |
| "min": -0.625, | |
| "max": 0.6562424284039121, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -18.680799961090088, | |
| "min": -64.89040005207062, | |
| "max": 53.10900020599365, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 609 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.018445094802882523, | |
| "min": 0.01035703014737616, | |
| "max": 0.023746898758690804, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.018445094802882523, | |
| "min": 0.01035703014737616, | |
| "max": 0.023746898758690804, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.11060444861650467, | |
| "min": 1.732775888285687e-06, | |
| "max": 0.12241433983047803, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.11060444861650467, | |
| "min": 1.732775888285687e-06, | |
| "max": 0.12241433983047803, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.1136261910200119, | |
| "min": 2.1583403925736397e-06, | |
| "max": 0.12581025809049606, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.1136261910200119, | |
| "min": 2.1583403925736397e-06, | |
| "max": 0.12581025809049606, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 290 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 290 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1677532344", | |
| "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/home/isaac/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.11.0", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1677538255" | |
| }, | |
| "total": 5910.890998768999, | |
| "count": 1, | |
| "self": 0.06460388699997566, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.026874823000071046, | |
| "count": 1, | |
| "self": 0.026874823000071046 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 5910.799520058999, | |
| "count": 1, | |
| "self": 4.6631930575777005, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.187994563994835, | |
| "count": 31, | |
| "self": 4.187994563994835 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 5901.793086253429, | |
| "count": 413789, | |
| "self": 4.565254165081569, | |
| "children": { | |
| "env_step": { | |
| "total": 4317.52626907742, | |
| "count": 413789, | |
| "self": 3338.7907093795748, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 975.8863963008871, | |
| "count": 413789, | |
| "self": 28.583583583496875, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 947.3028127173902, | |
| "count": 772554, | |
| "self": 947.3028127173902 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.8491633969579198, | |
| "count": 413789, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 5902.745093290739, | |
| "count": 413789, | |
| "is_parallel": true, | |
| "self": 3176.306758978216, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002331797000806546, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006164599999465281, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0017153370008600177, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0017153370008600177 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.019064633999732905, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005129329992996645, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0003821440004685428, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003821440004685428 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.01688135099993815, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.01688135099993815 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0012882060000265483, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0002719959984460729, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0010162100015804754, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0010162100015804754 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 2726.406486123524, | |
| "count": 413788, | |
| "is_parallel": true, | |
| "self": 165.69570598195514, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 112.6196814200166, | |
| "count": 413788, | |
| "is_parallel": true, | |
| "self": 112.6196814200166 | |
| }, | |
| "communicator.exchange": { | |
| "total": 2030.0720541379924, | |
| "count": 413788, | |
| "is_parallel": true, | |
| "self": 2030.0720541379924 | |
| }, | |
| "steps_from_proto": { | |
| "total": 418.01904458355966, | |
| "count": 827576, | |
| "is_parallel": true, | |
| "self": 79.1009894443232, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 338.91805513923646, | |
| "count": 3310304, | |
| "is_parallel": true, | |
| "self": 338.91805513923646 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.031848188998992555, | |
| "count": 60, | |
| "is_parallel": true, | |
| "self": 0.006230923997463833, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.025617265001528722, | |
| "count": 240, | |
| "is_parallel": true, | |
| "self": 0.025617265001528722 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1579.7015630109272, | |
| "count": 413789, | |
| "self": 36.488547004430075, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 520.3228761164983, | |
| "count": 413789, | |
| "self": 518.6864089684987, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.6364671479996105, | |
| "count": 12, | |
| "self": 1.6364671479996105 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1022.8901398899989, | |
| "count": 291, | |
| "self": 577.2819298669856, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 445.60821002301327, | |
| "count": 8722, | |
| "self": 445.60821002301327 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.979986887425184e-07, | |
| "count": 1, | |
| "self": 8.979986887425184e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.1552452859996265, | |
| "count": 1, | |
| "self": 0.0008733739996387158, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.1543719119999878, | |
| "count": 1, | |
| "self": 0.1543719119999878 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |