| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.6018836498260498, | |
| "min": 1.5453085899353027, | |
| "max": 3.295727014541626, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 32191.453125, | |
| "min": 23595.869140625, | |
| "max": 121191.859375, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 52.68131868131868, | |
| "min": 44.559633027522935, | |
| "max": 999.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19176.0, | |
| "min": 14064.0, | |
| "max": 26760.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1597.9941390638924, | |
| "min": 1198.7252374813206, | |
| "max": 1627.111825740658, | |
| "count": 965 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 290834.9333096284, | |
| "min": 2399.7320029860066, | |
| "max": 353036.22238567786, | |
| "count": 965 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 9999924.0, | |
| "min": 9398.0, | |
| "max": 9999924.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 9999924.0, | |
| "min": 9398.0, | |
| "max": 9999924.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.06568997353315353, | |
| "min": -0.11980075389146805, | |
| "max": 0.19735249876976013, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -12.021265029907227, | |
| "min": -17.609134674072266, | |
| "max": 33.94462966918945, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.06923780590295792, | |
| "min": -0.11975289136171341, | |
| "max": 0.20725135505199432, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -12.67051887512207, | |
| "min": -17.75794792175293, | |
| "max": 35.64723205566406, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.11840218826721274, | |
| "min": -0.7072088903850979, | |
| "max": 0.47907618965421406, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -21.667600452899933, | |
| "min": -60.839200139045715, | |
| "max": 76.35919976234436, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.11840218826721274, | |
| "min": -0.7072088903850979, | |
| "max": 0.47907618965421406, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -21.667600452899933, | |
| "min": -60.839200139045715, | |
| "max": 76.35919976234436, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.014544024500840655, | |
| "min": 0.009437778448530783, | |
| "max": 0.02323350603110157, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.014544024500840655, | |
| "min": 0.009437778448530783, | |
| "max": 0.02323350603110157, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.10801627139250437, | |
| "min": 2.033423588727601e-05, | |
| "max": 0.12143431057532629, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.10801627139250437, | |
| "min": 2.033423588727601e-05, | |
| "max": 0.12143431057532629, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.11004972979426383, | |
| "min": 2.0046720086005127e-05, | |
| "max": 0.12449382642904917, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.11004972979426383, | |
| "min": 2.0046720086005127e-05, | |
| "max": 0.12449382642904917, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 480 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 480 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1679857173", | |
| "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", | |
| "command_line_arguments": "/home/felipe/Documents/ML-Studies/HF-DeepRL/rl-course-huggingface/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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+cu113", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1679866742" | |
| }, | |
| "total": 9568.673476891, | |
| "count": 1, | |
| "self": 0.4911048750000191, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.016452390998892952, | |
| "count": 1, | |
| "self": 0.016452390998892952 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 9568.165919625, | |
| "count": 1, | |
| "self": 9.20331117276146, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.6472482859935553, | |
| "count": 40, | |
| "self": 3.6472482859935553 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 9555.147876447245, | |
| "count": 677259, | |
| "self": 9.58158161510437, | |
| "children": { | |
| "env_step": { | |
| "total": 6968.529440571041, | |
| "count": 677259, | |
| "self": 5069.581832214357, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1892.9330405239089, | |
| "count": 677259, | |
| "self": 53.27897592883164, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1839.6540645950772, | |
| "count": 1260758, | |
| "self": 1839.6540645950772 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 6.014567832775356, | |
| "count": 677259, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 9556.07453426981, | |
| "count": 677259, | |
| "is_parallel": true, | |
| "self": 5494.763372448691, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.001390330999129219, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0003180130006512627, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0010723179984779563, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0010723179984779563 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.014358135002112249, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003966290059906896, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0002613830001791939, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002613830001791939 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.012668479997955728, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.012668479997955728 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001031642997986637, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.000214303992834175, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.000817339005152462, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.000817339005152462 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 4061.270461069129, | |
| "count": 677258, | |
| "is_parallel": true, | |
| "self": 215.77667014224426, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 151.66650351202406, | |
| "count": 677258, | |
| "is_parallel": true, | |
| "self": 151.66650351202406 | |
| }, | |
| "communicator.exchange": { | |
| "total": 3029.6624329219558, | |
| "count": 677258, | |
| "is_parallel": true, | |
| "self": 3029.6624329219558 | |
| }, | |
| "steps_from_proto": { | |
| "total": 664.1648544929049, | |
| "count": 1354516, | |
| "is_parallel": true, | |
| "self": 138.21079235819707, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 525.9540621347078, | |
| "count": 5418064, | |
| "is_parallel": true, | |
| "self": 525.9540621347078 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.04070075198978884, | |
| "count": 78, | |
| "is_parallel": true, | |
| "self": 0.008413323947024764, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.03228742804276408, | |
| "count": 312, | |
| "is_parallel": true, | |
| "self": 0.03228742804276408 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 2577.0368542610995, | |
| "count": 677259, | |
| "self": 66.75755179104453, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 895.4636379140866, | |
| "count": 677259, | |
| "self": 891.6356066650915, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 3.828031248995103, | |
| "count": 20, | |
| "self": 3.828031248995103 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1614.8156645559684, | |
| "count": 480, | |
| "self": 938.8587034042539, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 675.9569611517145, | |
| "count": 14406, | |
| "self": 675.9569611517145 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0280018614139408e-06, | |
| "count": 1, | |
| "self": 1.0280018614139408e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.16748269099844038, | |
| "count": 1, | |
| "self": 0.0024151759971573483, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.16506751500128303, | |
| "count": 1, | |
| "self": 0.16506751500128303 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |