| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5607538819313049, |
| "min": 0.5607538819313049, |
| "max": 1.4721393585205078, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 16975.140625, |
| "min": 16975.140625, |
| "max": 44658.8203125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989997.0, |
| "min": 29952.0, |
| "max": 989997.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989997.0, |
| "min": 29952.0, |
| "max": 989997.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4093380868434906, |
| "min": -0.08303777873516083, |
| "max": 0.4333099126815796, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 107.24658203125, |
| "min": -19.929067611694336, |
| "max": 115.6937484741211, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.008611313067376614, |
| "min": -0.0023230514489114285, |
| "max": 0.1778278350830078, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.256164073944092, |
| "min": -0.5668245553970337, |
| "max": 42.678680419921875, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06647617579520947, |
| "min": 0.06647617579520947, |
| "max": 0.07469338694498502, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9306664611329325, |
| "min": 0.4972389220037289, |
| "max": 1.1182430086424573, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.011490370993747742, |
| "min": 5.9461949104773925e-05, |
| "max": 0.011490370993747742, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.1608651939124684, |
| "min": 0.0004162336437334175, |
| "max": 0.1608651939124684, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.2174847565050002e-05, |
| "min": 1.2174847565050002e-05, |
| "max": 0.0004919177159021714, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00017044786591070003, |
| "min": 0.00017044786591070003, |
| "max": 0.005845845230830998, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10243495, |
| "min": 0.10243495, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4340893, |
| "min": 1.3691136000000002, |
| "max": 2.569169, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025325150500000006, |
| "min": 0.00025325150500000006, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003545521070000001, |
| "min": 0.003545521070000001, |
| "max": 0.1169399831, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007329627405852079, |
| "min": 0.0072525120340287685, |
| "max": 0.29376915097236633, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10261478275060654, |
| "min": 0.10261478275060654, |
| "max": 2.0563840866088867, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 489.44827586206895, |
| "min": 447.93150684931504, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28388.0, |
| "min": 15984.0, |
| "max": 33986.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.269106869682156, |
| "min": -1.0000000521540642, |
| "max": 1.4150465500273117, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 73.60819844156504, |
| "min": -32.000001668930054, |
| "max": 103.29839815199375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.269106869682156, |
| "min": -1.0000000521540642, |
| "max": 1.4150465500273117, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 73.60819844156504, |
| "min": -32.000001668930054, |
| "max": 103.29839815199375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.0385565430599321, |
| "min": 0.03487188973318951, |
| "max": 6.6248966390267015, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.236279497476062, |
| "min": 2.236279497476062, |
| "max": 105.99834622442722, |
| "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": "1733350254", |
| "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.5.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1733352690" |
| }, |
| "total": 2436.0228963810005, |
| "count": 1, |
| "self": 0.476227614000436, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0550537300000542, |
| "count": 1, |
| "self": 0.0550537300000542 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2435.491615037, |
| "count": 1, |
| "self": 1.2045015581070402, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.2254129400002967, |
| "count": 1, |
| "self": 2.2254129400002967 |
| }, |
| "TrainerController.advance": { |
| "total": 2431.938881308892, |
| "count": 63418, |
| "self": 1.231301679995795, |
| "children": { |
| "env_step": { |
| "total": 1357.3508736538734, |
| "count": 63418, |
| "self": 1212.2243854658554, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 144.4094961409969, |
| "count": 63418, |
| "self": 4.361333081028079, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 140.04816305996883, |
| "count": 62572, |
| "self": 140.04816305996883 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7169920470209945, |
| "count": 63418, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2431.3389831890477, |
| "count": 63418, |
| "is_parallel": true, |
| "self": 1326.4456433600244, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002171028000248043, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006978979990890366, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014731300011590065, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014731300011590065 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05028377700000419, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000610336000136158, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047343100004582084, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047343100004582084 |
| }, |
| "communicator.exchange": { |
| "total": 0.04762056900017342, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04762056900017342 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015794409996487957, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000336123000124644, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012433179995241517, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012433179995241517 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1104.8933398290233, |
| "count": 63417, |
| "is_parallel": true, |
| "self": 32.005598079937954, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.002013966997765, |
| "count": 63417, |
| "is_parallel": true, |
| "self": 23.002013966997765 |
| }, |
| "communicator.exchange": { |
| "total": 955.9179077400609, |
| "count": 63417, |
| "is_parallel": true, |
| "self": 955.9179077400609 |
| }, |
| "steps_from_proto": { |
| "total": 93.96782004202669, |
| "count": 63417, |
| "is_parallel": true, |
| "self": 18.24095071277725, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 75.72686932924944, |
| "count": 507336, |
| "is_parallel": true, |
| "self": 75.72686932924944 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1073.356705975023, |
| "count": 63418, |
| "self": 2.298255489083658, |
| "children": { |
| "process_trajectory": { |
| "total": 127.63171706194453, |
| "count": 63418, |
| "self": 127.33218434294395, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.299532719000581, |
| "count": 2, |
| "self": 0.299532719000581 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 943.4267334239948, |
| "count": 449, |
| "self": 514.2739512840399, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 429.152782139955, |
| "count": 37960, |
| "self": 429.152782139955 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0960002327919938e-06, |
| "count": 1, |
| "self": 1.0960002327919938e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.12281813400022656, |
| "count": 1, |
| "self": 0.002169604000300751, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.12064852999992581, |
| "count": 1, |
| "self": 0.12064852999992581 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
