| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.6076599955558777, |
| "min": 0.5923882722854614, |
| "max": 1.4416825771331787, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 18317.302734375, |
| "min": 17800.08203125, |
| "max": 43734.8828125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989909.0, |
| "min": 29952.0, |
| "max": 989909.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989909.0, |
| "min": 29952.0, |
| "max": 989909.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.19271090626716614, |
| "min": -0.09983684867620468, |
| "max": 0.19271090626716614, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 49.14128112792969, |
| "min": -24.060680389404297, |
| "max": 49.14128112792969, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.011703865602612495, |
| "min": -0.011703865602612495, |
| "max": 0.461391806602478, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -2.984485626220703, |
| "min": -2.984485626220703, |
| "max": 109.34986114501953, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06882973944909906, |
| "min": 0.06428515679355913, |
| "max": 0.0725272628219178, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9636163522873868, |
| "min": 0.49143051600064314, |
| "max": 1.0407014043303209, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.010227514696087842, |
| "min": 0.0004155907063713054, |
| "max": 0.010227514696087842, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.14318520574522978, |
| "min": 0.004987088476455665, |
| "max": 0.14318520574522978, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.73212599408572e-06, |
| "min": 7.73212599408572e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010824976391720009, |
| "min": 0.00010824976391720009, |
| "max": 0.0035071160309613995, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10257734285714284, |
| "min": 0.10257734285714284, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4360827999999999, |
| "min": 1.3886848, |
| "max": 2.5690386000000007, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00026747655142857164, |
| "min": 0.00026747655142857164, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003744671720000003, |
| "min": 0.003744671720000003, |
| "max": 0.11692695614000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012460383586585522, |
| "min": 0.012460383586585522, |
| "max": 0.45620039105415344, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17444537580013275, |
| "min": 0.17444537580013275, |
| "max": 3.1934027671813965, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 613.44, |
| "min": 613.44, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30672.0, |
| "min": 15984.0, |
| "max": 33903.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 0.906371957808733, |
| "min": -1.0000000521540642, |
| "max": 0.906371957808733, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 45.31859789043665, |
| "min": -30.997401610016823, |
| "max": 45.31859789043665, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 0.906371957808733, |
| "min": -1.0000000521540642, |
| "max": 0.906371957808733, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 45.31859789043665, |
| "min": -30.997401610016823, |
| "max": 45.31859789043665, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.08027245839359239, |
| "min": 0.08027245839359239, |
| "max": 9.600501103326678, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.013622919679619, |
| "min": 3.954603912192397, |
| "max": 153.60801765322685, |
| "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": "1741775156", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1741777255" |
| }, |
| "total": 2098.765049498, |
| "count": 1, |
| "self": 0.47583024199957435, |
| "children": { |
| "run_training.setup": { |
| "total": 0.019627852999974493, |
| "count": 1, |
| "self": 0.019627852999974493 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2098.269591403, |
| "count": 1, |
| "self": 1.4140341899328632, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.086692922999873, |
| "count": 1, |
| "self": 2.086692922999873 |
| }, |
| "TrainerController.advance": { |
| "total": 2094.6693355450675, |
| "count": 63237, |
| "self": 1.4236951751172455, |
| "children": { |
| "env_step": { |
| "total": 1409.9440794779837, |
| "count": 63237, |
| "self": 1252.5133927619988, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 156.6518227599911, |
| "count": 63237, |
| "self": 4.750612389946355, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 151.90121037004474, |
| "count": 62548, |
| "self": 151.90121037004474 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7788639559937565, |
| "count": 63237, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2093.2051340440585, |
| "count": 63237, |
| "is_parallel": true, |
| "self": 953.9215038749646, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020757789998242515, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007017570001153217, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013740219997089298, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013740219997089298 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04972740899984274, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005311619997883099, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00042652000001908164, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00042652000001908164 |
| }, |
| "communicator.exchange": { |
| "total": 0.04708492700001443, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04708492700001443 |
| }, |
| "steps_from_proto": { |
| "total": 0.001684800000020914, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036008499978379405, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00132471500023712, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00132471500023712 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1139.2836301690938, |
| "count": 63236, |
| "is_parallel": true, |
| "self": 31.777482157082204, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.79776340301919, |
| "count": 63236, |
| "is_parallel": true, |
| "self": 23.79776340301919 |
| }, |
| "communicator.exchange": { |
| "total": 985.0672462029918, |
| "count": 63236, |
| "is_parallel": true, |
| "self": 985.0672462029918 |
| }, |
| "steps_from_proto": { |
| "total": 98.64113840600066, |
| "count": 63236, |
| "is_parallel": true, |
| "self": 19.955688728202404, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 78.68544967779826, |
| "count": 505888, |
| "is_parallel": true, |
| "self": 78.68544967779826 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 683.3015608919666, |
| "count": 63237, |
| "self": 2.5237451669374877, |
| "children": { |
| "process_trajectory": { |
| "total": 128.80714049303242, |
| "count": 63237, |
| "self": 128.60319254903243, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20394794399999228, |
| "count": 2, |
| "self": 0.20394794399999228 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 551.9706752319967, |
| "count": 446, |
| "self": 306.394864768052, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 245.57581046394466, |
| "count": 22812, |
| "self": 245.57581046394466 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.819997674436308e-07, |
| "count": 1, |
| "self": 8.819997674436308e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09952786299982108, |
| "count": 1, |
| "self": 0.001698620999832201, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09782924199998888, |
| "count": 1, |
| "self": 0.09782924199998888 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
