Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Instructions to use hunter002/ppo-SnowballTarget with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use hunter002/ppo-SnowballTarget with ml-agents:
mlagents-load-from-hf --repo-id="hunter002/ppo-SnowballTarget" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from hunter002/ppo-SnowballTarget: direct link, hf CLI and curl.
- Browser
- Download file 17.6 kB
-
https://huggingface.co/hunter002/ppo-SnowballTarget/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://hunter002/ppo-SnowballTarget/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/hunter002/ppo-SnowballTarget/resolve/main/run_logs/timers.json
17.6 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "SnowballTarget.Policy.Entropy.mean": { | |
| "value": 0.9205897450447083, | |
| "min": 0.9205897450447083, | |
| "max": 2.8262743949890137, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Entropy.sum": { | |
| "value": 8749.28515625, | |
| "min": 8749.28515625, | |
| "max": 28850.609375, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Step.mean": { | |
| "value": 199984.0, | |
| "min": 9952.0, | |
| "max": 199984.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Step.sum": { | |
| "value": 199984.0, | |
| "min": 9952.0, | |
| "max": 199984.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 12.522320747375488, | |
| "min": 0.4018811583518982, | |
| "max": 12.522320747375488, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 2441.8525390625, | |
| "min": 77.9649429321289, | |
| "max": 2514.4765625, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.PolicyLoss.mean": { | |
| "value": 0.06589039159692167, | |
| "min": 0.061047213902080934, | |
| "max": 0.07189999160633022, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.PolicyLoss.sum": { | |
| "value": 0.2635615663876867, | |
| "min": 0.24418885560832373, | |
| "max": 0.3594999580316511, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.ValueLoss.mean": { | |
| "value": 0.24857467434862082, | |
| "min": 0.13742467128059954, | |
| "max": 0.3745834432396234, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.ValueLoss.sum": { | |
| "value": 0.9942986973944833, | |
| "min": 0.5496986851223982, | |
| "max": 1.872917216198117, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.LearningRate.mean": { | |
| "value": 8.082097306000005e-06, | |
| "min": 8.082097306000005e-06, | |
| "max": 0.000291882002706, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.LearningRate.sum": { | |
| "value": 3.232838922400002e-05, | |
| "min": 3.232838922400002e-05, | |
| "max": 0.00138516003828, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Epsilon.mean": { | |
| "value": 0.10269400000000001, | |
| "min": 0.10269400000000001, | |
| "max": 0.19729400000000002, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Epsilon.sum": { | |
| "value": 0.41077600000000003, | |
| "min": 0.41077600000000003, | |
| "max": 0.96172, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Beta.mean": { | |
| "value": 0.0001444306000000001, | |
| "min": 0.0001444306000000001, | |
| "max": 0.0048649706, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Beta.sum": { | |
| "value": 0.0005777224000000004, | |
| "min": 0.0005777224000000004, | |
| "max": 0.023089828, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.EpisodeLength.mean": { | |
| "value": 199.0, | |
| "min": 199.0, | |
| "max": 199.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.EpisodeLength.sum": { | |
| "value": 8756.0, | |
| "min": 8756.0, | |
| "max": 10945.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.CumulativeReward.mean": { | |
| "value": 25.272727272727273, | |
| "min": 3.8863636363636362, | |
| "max": 25.545454545454547, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.CumulativeReward.sum": { | |
| "value": 1112.0, | |
| "min": 171.0, | |
| "max": 1373.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { | |
| "value": 25.272727272727273, | |
| "min": 3.8863636363636362, | |
| "max": 25.545454545454547, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { | |
| "value": 1112.0, | |
| "min": 171.0, | |
| "max": 1373.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1795092920", | |
| "python_version": "3.10.22 (main, Oct 1 2026, 15:39:47) [GCC 13.3.0]", | |
| "command_line_arguments": "/content/mlagents_env/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --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": "1795093473" | |
| }, | |
| "total": 553.491259162, | |
| "count": 1, | |
| "self": 0.5393491419999918, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.050548908000109805, | |
| "count": 1, | |
| "self": 0.050548908000109805 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 552.9013611119999, | |
| "count": 1, | |
| "self": 0.4295941929813125, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.255163562999769, | |
| "count": 1, | |
| "self": 4.255163562999769 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 548.1208581670189, | |
| "count": 18192, | |
| "self": 0.47901754096710647, | |
| "children": { | |
| "env_step": { | |
| "total": 405.07373846404244, | |
| "count": 18192, | |
| "self": 318.0247959859935, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 86.7780682980333, | |
| "count": 18192, | |
| "self": 1.563830393983153, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 85.21423790405015, | |
| "count": 18192, | |
| "self": 85.21423790405015 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.2708741800156531, | |
| "count": 18192, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 550.3683498309701, | |
| "count": 18192, | |
| "is_parallel": true, | |
| "self": 270.71508031098483, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.005893156000183808, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0032846860003701295, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0026084699998136784, | |
| "count": 10, | |
| "is_parallel": true, | |
| "self": 0.0026084699998136784 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04347975700011375, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008290110004054441, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004996530001335486, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004996530001335486 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.0397039509998649, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0397039509998649 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0024471419997098565, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004390910003166937, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.002008050999393163, | |
| "count": 10, | |
| "is_parallel": true, | |
| "self": 0.002008050999393163 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 279.6532695199853, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 12.60286959391442, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 6.6159621250590135, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 6.6159621250590135 | |
| }, | |
| "communicator.exchange": { | |
| "total": 212.2433482800143, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 212.2433482800143 | |
| }, | |
| "steps_from_proto": { | |
| "total": 48.19108952099759, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 7.864598604092862, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 40.32649091690473, | |
| "count": 181910, | |
| "is_parallel": true, | |
| "self": 40.32649091690473 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 142.56810216200938, | |
| "count": 18192, | |
| "self": 0.5340056199784158, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 30.097036289032076, | |
| "count": 18192, | |
| "self": 29.523722639031803, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5733136500002729, | |
| "count": 4, | |
| "self": 0.5733136500002729 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 111.93706025299889, | |
| "count": 90, | |
| "self": 48.397863168992444, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 63.539197084006446, | |
| "count": 4587, | |
| "self": 63.539197084006446 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.252999936696142e-06, | |
| "count": 1, | |
| "self": 1.252999936696142e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09574393599996256, | |
| "count": 1, | |
| "self": 0.0009554449998177006, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09478849100014486, | |
| "count": 1, | |
| "self": 0.09478849100014486 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |