| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2945275604724884, |
| "min": 0.2945275604724884, |
| "max": 1.4150532484054565, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8798.126953125, |
| "min": 8798.126953125, |
| "max": 42927.0546875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989981.0, |
| "min": 29950.0, |
| "max": 989981.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989981.0, |
| "min": 29950.0, |
| "max": 989981.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.679139256477356, |
| "min": -0.13607457280158997, |
| "max": 0.679139256477356, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 196.95037841796875, |
| "min": -32.65789794921875, |
| "max": 196.95037841796875, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.018701819702982903, |
| "min": -0.0019406556384637952, |
| "max": 0.7785513401031494, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.423527717590332, |
| "min": -0.520095705986023, |
| "max": 184.51666259765625, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06923439229269408, |
| "min": 0.06334820178288318, |
| "max": 0.07317486656053612, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0385158843904112, |
| "min": 0.4877481737781929, |
| "max": 1.097622998408042, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016657009090219315, |
| "min": 0.00040498373932602725, |
| "max": 0.033317399746503606, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2498551363532897, |
| "min": 0.0044548211325863, |
| "max": 0.2498551363532897, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.514457495213332e-06, |
| "min": 7.514457495213332e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011271686242819999, |
| "min": 0.00011271686242819999, |
| "max": 0.0035093570302144, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10250478666666667, |
| "min": 0.10250478666666667, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5375718, |
| "min": 1.3886848, |
| "max": 2.5697856000000003, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00026022818800000005, |
| "min": 0.00026022818800000005, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0039034228200000008, |
| "min": 0.0039034228200000008, |
| "max": 0.11700158144, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013486376963555813, |
| "min": 0.013204602524638176, |
| "max": 0.6791519522666931, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.20229566097259521, |
| "min": 0.18486443161964417, |
| "max": 4.754063606262207, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 275.8198198198198, |
| "min": 275.8198198198198, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30616.0, |
| "min": 16877.0, |
| "max": 32101.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.688140525742694, |
| "min": -0.9999677942645165, |
| "max": 1.688140525742694, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 187.38359835743904, |
| "min": -30.999001622200012, |
| "max": 187.38359835743904, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.688140525742694, |
| "min": -0.9999677942645165, |
| "max": 1.688140525742694, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 187.38359835743904, |
| "min": -30.999001622200012, |
| "max": 187.38359835743904, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.03842139031660957, |
| "min": 0.03842139031660957, |
| "max": 14.61289706124979, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.264774325143662, |
| "min": 4.03263636934571, |
| "max": 248.4192500412464, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1724214793", |
| "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.3.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1724218288" |
| }, |
| "total": 3495.567355605, |
| "count": 1, |
| "self": 1.8236455599999317, |
| "children": { |
| "run_training.setup": { |
| "total": 0.07707505200005471, |
| "count": 1, |
| "self": 0.07707505200005471 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3493.666634993, |
| "count": 1, |
| "self": 2.329555968941804, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.936078357000042, |
| "count": 1, |
| "self": 2.936078357000042 |
| }, |
| "TrainerController.advance": { |
| "total": 3488.285350805059, |
| "count": 64014, |
| "self": 2.6271795521415697, |
| "children": { |
| "env_step": { |
| "total": 2311.1773647659556, |
| "count": 64014, |
| "self": 2136.1786085578397, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 173.52489663804454, |
| "count": 64014, |
| "self": 7.759756877075006, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 165.76513976096953, |
| "count": 62536, |
| "self": 165.76513976096953 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.4738595700712267, |
| "count": 64014, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3485.7812506209816, |
| "count": 64014, |
| "is_parallel": true, |
| "self": 1546.5985971219006, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.003625230999887208, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.001238690000036513, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002386540999850695, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002386540999850695 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06890099399993233, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008509750000484928, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005889149999802612, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005889149999802612 |
| }, |
| "communicator.exchange": { |
| "total": 0.06524836800008416, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.06524836800008416 |
| }, |
| "steps_from_proto": { |
| "total": 0.002212735999819415, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00043577299970820604, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0017769630001112091, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0017769630001112091 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1939.182653499081, |
| "count": 64013, |
| "is_parallel": true, |
| "self": 51.93104833404732, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 31.660981431008622, |
| "count": 64013, |
| "is_parallel": true, |
| "self": 31.660981431008622 |
| }, |
| "communicator.exchange": { |
| "total": 1720.38899617594, |
| "count": 64013, |
| "is_parallel": true, |
| "self": 1720.38899617594 |
| }, |
| "steps_from_proto": { |
| "total": 135.20162755808497, |
| "count": 64013, |
| "is_parallel": true, |
| "self": 29.607368934370243, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 105.59425862371472, |
| "count": 512104, |
| "is_parallel": true, |
| "self": 105.59425862371472 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1174.4808064869617, |
| "count": 64014, |
| "self": 4.940582770967694, |
| "children": { |
| "process_trajectory": { |
| "total": 178.0186522509896, |
| "count": 64014, |
| "self": 177.73141616598946, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2872360850001314, |
| "count": 2, |
| "self": 0.2872360850001314 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 991.5215714650044, |
| "count": 454, |
| "self": 396.5653028389672, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 594.9562686260372, |
| "count": 22788, |
| "self": 594.9562686260372 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0999992809956893e-06, |
| "count": 1, |
| "self": 1.0999992809956893e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.11564876200009166, |
| "count": 1, |
| "self": 0.0033055920002880157, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.11234316999980365, |
| "count": 1, |
| "self": 0.11234316999980365 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
