Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use alan1009/ppo-Pyramids-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use alan1009/ppo-Pyramids-v1 with ml-agents:
mlagents-load-from-hf --repo-id="alan1009/ppo-Pyramids-v1" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from alan1009/ppo-Pyramids-v1: direct link, hf CLI and curl.
- Browser
- Download file 18.7 kB
-
https://huggingface.co/alan1009/ppo-Pyramids-v1/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://alan1009/ppo-Pyramids-v1/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/alan1009/ppo-Pyramids-v1/resolve/main/run_logs/timers.json
18.7 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.60909503698349, | |
| "min": 0.60909503698349, | |
| "max": 1.4291146993637085, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 18409.2890625, | |
| "min": 18243.662109375, | |
| "max": 43353.625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989923.0, | |
| "min": 29952.0, | |
| "max": 989923.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989923.0, | |
| "min": 29952.0, | |
| "max": 989923.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.2510603070259094, | |
| "min": -0.0785120502114296, | |
| "max": 0.2847936153411865, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 64.7735595703125, | |
| "min": -18.87786865234375, | |
| "max": 73.47675323486328, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": -0.0066003939136862755, | |
| "min": -0.008350602351129055, | |
| "max": 0.3255818486213684, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": -1.7029016017913818, | |
| "min": -2.137754201889038, | |
| "max": 77.16289520263672, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06985563660920079, | |
| "min": 0.06454104009095492, | |
| "max": 0.07318373439429655, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0478345491380119, | |
| "min": 0.48053088136573974, | |
| "max": 1.0864822172899913, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.012339213270267161, | |
| "min": 0.0007072238709693302, | |
| "max": 0.012339213270267161, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.18508819905400742, | |
| "min": 0.007164433692062936, | |
| "max": 0.18508819905400742, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.54575748478e-06, | |
| "min": 7.54575748478e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0001131863622717, | |
| "min": 0.0001131863622717, | |
| "max": 0.0033759502746833, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10251522, | |
| "min": 0.10251522, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5377283000000002, | |
| "min": 1.3886848, | |
| "max": 2.4826908000000003, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00026127047799999996, | |
| "min": 0.00026127047799999996, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003919057169999999, | |
| "min": 0.003919057169999999, | |
| "max": 0.11254913833, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.010006909258663654, | |
| "min": 0.010006909258663654, | |
| "max": 0.4302816092967987, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1501036435365677, | |
| "min": 0.1440466195344925, | |
| "max": 3.0119712352752686, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 549.5263157894736, | |
| "min": 549.5263157894736, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 31323.0, | |
| "min": 15984.0, | |
| "max": 32797.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.0643578718105953, | |
| "min": -1.0000000521540642, | |
| "max": 1.0643578718105953, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 60.668398693203926, | |
| "min": -31.99920167028904, | |
| "max": 60.668398693203926, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.0643578718105953, | |
| "min": -1.0000000521540642, | |
| "max": 1.0643578718105953, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 60.668398693203926, | |
| "min": -31.99920167028904, | |
| "max": 60.668398693203926, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.05687562511261683, | |
| "min": 0.05687562511261683, | |
| "max": 9.274238020181656, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.2419106314191595, | |
| "min": 3.1551167535508284, | |
| "max": 148.3878083229065, | |
| "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": "1793011334", | |
| "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": "2.8.0+cu128", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1793012047" | |
| }, | |
| "total": 712.624701495, | |
| "count": 1, | |
| "self": 0.21703362300013396, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.010790937999900052, | |
| "count": 1, | |
| "self": 0.010790937999900052 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 712.3968769339999, | |
| "count": 1, | |
| "self": 0.5355456829947798, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.0049376540000594, | |
| "count": 1, | |
| "self": 1.0049376540000594 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 710.8283790640053, | |
| "count": 63360, | |
| "self": 0.49646763299006125, | |
| "children": { | |
| "env_step": { | |
| "total": 478.86282120197757, | |
| "count": 63360, | |
| "self": 424.18979560094635, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 54.33114111100326, | |
| "count": 63360, | |
| "self": 1.8156076830316579, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 52.515533427971604, | |
| "count": 62567, | |
| "self": 52.515533427971604 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.34188449002795096, | |
| "count": 63360, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 711.4705508950574, | |
| "count": 63360, | |
| "is_parallel": true, | |
| "self": 322.1959959340388, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0006960799998978473, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00019897999982276815, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0004971000000750792, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0004971000000750792 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.018509214999994583, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0001463700002659607, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00017873999991024903, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00017873999991024903 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.016810785999950895, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.016810785999950895 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0013733189998674789, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00011926999968636665, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012540490001811122, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012540490001811122 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 389.27455496101857, | |
| "count": 63359, | |
| "is_parallel": true, | |
| "self": 7.241343654993216, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 4.743611734994147, | |
| "count": 63359, | |
| "is_parallel": true, | |
| "self": 4.743611734994147 | |
| }, | |
| "communicator.exchange": { | |
| "total": 357.4568921880159, | |
| "count": 63359, | |
| "is_parallel": true, | |
| "self": 357.4568921880159 | |
| }, | |
| "steps_from_proto": { | |
| "total": 19.832707383015304, | |
| "count": 63359, | |
| "is_parallel": true, | |
| "self": 4.000156306994768, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 15.832551076020536, | |
| "count": 506872, | |
| "is_parallel": true, | |
| "self": 15.832551076020536 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 231.46909022903765, | |
| "count": 63360, | |
| "self": 0.8687278770546527, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 45.3615305679823, | |
| "count": 63360, | |
| "self": 45.29049424498248, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.07103632299981655, | |
| "count": 2, | |
| "self": 0.07103632299981655 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 185.2388317840007, | |
| "count": 448, | |
| "self": 104.7906444140026, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 80.4481873699981, | |
| "count": 22773, | |
| "self": 80.4481873699981 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.799998573114863e-07, | |
| "count": 1, | |
| "self": 6.799998573114863e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.02801385299994763, | |
| "count": 1, | |
| "self": 0.0004543200000171055, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.027559532999930525, | |
| "count": 1, | |
| "self": 0.027559532999930525 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |