Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use Abuudiii/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use Abuudiii/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="Abuudiii/ppo-Pyramids" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from Abuudiii/ppo-Pyramids: direct link, hf CLI and curl.
- Browser
- Download file 18.8 kB
-
https://huggingface.co/Abuudiii/ppo-Pyramids/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://Abuudiii/ppo-Pyramids/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/Abuudiii/ppo-Pyramids/resolve/main/run_logs/timers.json
18.8 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.30431222915649414, | |
| "min": 0.2997888922691345, | |
| "max": 0.6104104518890381, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 9080.6767578125, | |
| "min": 8960.0908203125, | |
| "max": 16852.814453125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 1979898.0, | |
| "min": 1019966.0, | |
| "max": 1979898.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 1979898.0, | |
| "min": 1019966.0, | |
| "max": 1979898.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.6447826623916626, | |
| "min": 0.19637173414230347, | |
| "max": 0.6562128663063049, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 184.4078369140625, | |
| "min": 33.053504943847656, | |
| "max": 190.95794677734375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.03329402953386307, | |
| "min": -0.01989748328924179, | |
| "max": 0.05321849510073662, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 9.522092819213867, | |
| "min": -3.5995655059814453, | |
| "max": 15.220489501953125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 285.9191919191919, | |
| "min": 285.9191919191919, | |
| "max": 680.25, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28306.0, | |
| "min": 14965.0, | |
| "max": 32524.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.673664635028502, | |
| "min": 0.7740999665111303, | |
| "max": 1.7028437301826973, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 165.6927988678217, | |
| "min": 25.028599098324776, | |
| "max": 175.2287978231907, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.673664635028502, | |
| "min": 0.7740999665111303, | |
| "max": 1.7028437301826973, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 165.6927988678217, | |
| "min": 25.028599098324776, | |
| "max": 175.2287978231907, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.02022557739418875, | |
| "min": 0.02022557739418875, | |
| "max": 0.07436142470065864, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.002332162024686, | |
| "min": 1.7513342385645956, | |
| "max": 3.384325666411314, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06973685804543839, | |
| "min": 0.06500511600530617, | |
| "max": 0.07271041034532355, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9763160126361374, | |
| "min": 0.63117190303966, | |
| "max": 1.0808707605853367, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.015258209392500466, | |
| "min": 0.00792006672989893, | |
| "max": 0.016616935935194813, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.21361493149500652, | |
| "min": 0.07130846138695147, | |
| "max": 0.2492540390279222, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 5.368051782110717e-06, | |
| "min": 5.368051782110717e-06, | |
| "max": 0.00014838731720424444, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 7.515272494955003e-05, | |
| "min": 7.515272494955003e-05, | |
| "max": 0.0020259193246938, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10178931785714287, | |
| "min": 0.10178931785714287, | |
| "max": 0.14946242222222225, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4250504500000003, | |
| "min": 1.3451618000000003, | |
| "max": 2.1336969, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00018875285392857153, | |
| "min": 0.00018875285392857153, | |
| "max": 0.00495129598, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0026425399550000016, | |
| "min": 0.0026425399550000016, | |
| "max": 0.06760308938, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.006828136742115021, | |
| "min": 0.0067711458541452885, | |
| "max": 0.011052335612475872, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.09559391438961029, | |
| "min": 0.09479603916406631, | |
| "max": 0.15666170418262482, | |
| "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": "1793254484", | |
| "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", | |
| "command_line_arguments": "/home/AMD/absheikh/rl-experiments/mlagents/.venv/bin/mlagents-learn PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --torch-device cuda --resume", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.8.0+rocm6.4", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1793257088" | |
| }, | |
| "total": 2604.074793931097, | |
| "count": 1, | |
| "self": 0.47742811031639576, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.06643028743565083, | |
| "count": 1, | |
| "self": 0.06643028743565083 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2603.5309355333447, | |
| "count": 1, | |
| "self": 1.311373831704259, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.610912276431918, | |
| "count": 1, | |
| "self": 3.610912276431918 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2598.485748678446, | |
| "count": 64651, | |
| "self": 1.1605321392416954, | |
| "children": { | |
| "env_step": { | |
| "total": 1845.6751594077796, | |
| "count": 64651, | |
| "self": 1708.3011282663792, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 136.59161848947406, | |
| "count": 64651, | |
| "self": 3.7545344568789005, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 132.83708403259516, | |
| "count": 62552, | |
| "self": 132.83708403259516 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.7824126519262791, | |
| "count": 64651, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2599.9442357458174, | |
| "count": 64651, | |
| "is_parallel": true, | |
| "self": 1010.6800258178264, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002752605825662613, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008014291524887085, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0019511766731739044, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0019511766731739044 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04453127086162567, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008446723222732544, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004619453102350235, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004619453102350235 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04079294949769974, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04079294949769974 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.002431703731417656, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005485024303197861, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0018832013010978699, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0018832013010978699 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1589.264209927991, | |
| "count": 64650, | |
| "is_parallel": true, | |
| "self": 49.84520725347102, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 35.33832837827504, | |
| "count": 64650, | |
| "is_parallel": true, | |
| "self": 35.33832837827504 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1363.4573536273092, | |
| "count": 64650, | |
| "is_parallel": true, | |
| "self": 1363.4573536273092 | |
| }, | |
| "steps_from_proto": { | |
| "total": 140.62332066893578, | |
| "count": 64650, | |
| "is_parallel": true, | |
| "self": 30.173125511035323, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 110.45019515790045, | |
| "count": 517200, | |
| "is_parallel": true, | |
| "self": 110.45019515790045 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 751.6500571314245, | |
| "count": 64651, | |
| "self": 2.5493362862616777, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 101.81671574153006, | |
| "count": 64651, | |
| "self": 101.53502881899476, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.28168692253530025, | |
| "count": 2, | |
| "self": 0.28168692253530025 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 647.2840051036328, | |
| "count": 473, | |
| "self": 306.71699279360473, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 340.5670123100281, | |
| "count": 22770, | |
| "self": 340.5670123100281 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.2423843145370483e-06, | |
| "count": 1, | |
| "self": 1.2423843145370483e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.122899504378438, | |
| "count": 1, | |
| "self": 0.015762997791171074, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.10713650658726692, | |
| "count": 1, | |
| "self": 0.10713650658726692 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |