Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use turhancan97/testpyramidsrnd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use turhancan97/testpyramidsrnd with ml-agents:
mlagents-load-from-hf --repo-id="turhancan97/testpyramidsrnd" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from turhancan97/testpyramidsrnd: direct link, hf CLI and curl.
- Browser
- Download file 18.8 kB
-
https://huggingface.co/turhancan97/testpyramidsrnd/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://turhancan97/testpyramidsrnd/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/turhancan97/testpyramidsrnd/resolve/main/run_logs/timers.json
18.8 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.7669917941093445, | |
| "min": 0.7669917941093445, | |
| "max": 1.4810545444488525, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 23500.62890625, | |
| "min": 23500.62890625, | |
| "max": 44929.26953125, | |
| "count": 8 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 239958.0, | |
| "min": 29974.0, | |
| "max": 239958.0, | |
| "count": 8 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 239958.0, | |
| "min": 29974.0, | |
| "max": 239958.0, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.08021598309278488, | |
| "min": -0.10526439547538757, | |
| "max": 0.006860638968646526, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -19.57270050048828, | |
| "min": -25.473983764648438, | |
| "max": 1.6328320503234863, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.03885841742157936, | |
| "min": 0.03885841742157936, | |
| "max": 0.28153514862060547, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 9.481453895568848, | |
| "min": 9.481453895568848, | |
| "max": 67.00536346435547, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07220267972760229, | |
| "min": 0.0672382620456064, | |
| "max": 0.07328388441462232, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9386348364588297, | |
| "min": 0.5129871909023562, | |
| "max": 0.9386348364588297, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.0023970643957495386, | |
| "min": 0.00013133329527695973, | |
| "max": 0.004100341063228366, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.031161837144744003, | |
| "min": 0.0014446662480465569, | |
| "max": 0.031161837144744003, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 2.94312901896e-05, | |
| "min": 2.94312901896e-05, | |
| "max": 0.00028060252075154277, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0003826067724648, | |
| "min": 0.0003826067724648, | |
| "max": 0.0027170185943272006, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1098104, | |
| "min": 0.1098104, | |
| "max": 0.19353417142857146, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4275352000000001, | |
| "min": 1.3547392000000003, | |
| "max": 2.0056728, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0009900589599999999, | |
| "min": 0.0009900589599999999, | |
| "max": 0.009354063725714288, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.012870766479999999, | |
| "min": 0.012870766479999999, | |
| "max": 0.09058671272000002, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.03127488121390343, | |
| "min": 0.03127488121390343, | |
| "max": 0.33825868368148804, | |
| "count": 8 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.40657344460487366, | |
| "min": 0.40657344460487366, | |
| "max": 2.3678107261657715, | |
| "count": 8 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 960.8787878787879, | |
| "min": 955.4545454545455, | |
| "max": 999.0, | |
| "count": 8 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 31709.0, | |
| "min": 16773.0, | |
| "max": 31968.0, | |
| "count": 8 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": -0.6585818630727854, | |
| "min": -0.9999375520274043, | |
| "max": -0.6585818630727854, | |
| "count": 8 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": -21.73320148140192, | |
| "min": -31.998001664876938, | |
| "max": -14.789000898599625, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": -0.6585818630727854, | |
| "min": -0.9999375520274043, | |
| "max": -0.6585818630727854, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": -21.73320148140192, | |
| "min": -31.998001664876938, | |
| "max": -14.789000898599625, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.3107151434347598, | |
| "min": 0.3107151434347598, | |
| "max": 6.8928938650471325, | |
| "count": 8 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 10.253599733347073, | |
| "min": 10.253599733347073, | |
| "max": 117.17919570580125, | |
| "count": 8 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 8 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 8 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1659354850", | |
| "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", | |
| "mlagents_version": "0.29.0.dev0", | |
| "mlagents_envs_version": "0.29.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.8.1+cu102", | |
| "numpy_version": "1.21.6", | |
| "end_time_seconds": "1659355350" | |
| }, | |
| "total": 499.16679812100006, | |
| "count": 1, | |
| "self": 0.48353962600003797, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.046288968999988356, | |
| "count": 1, | |
| "self": 0.046288968999988356 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 498.63696952600003, | |
| "count": 1, | |
| "self": 0.40598806899595274, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 10.23266580500001, | |
| "count": 1, | |
| "self": 10.23266580500001 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 487.88847962400405, | |
| "count": 15708, | |
| "self": 0.432629593003071, | |
| "children": { | |
| "env_step": { | |
| "total": 304.30467526898906, | |
| "count": 15708, | |
| "self": 272.7768432099872, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 31.306041705999064, | |
| "count": 15708, | |
| "self": 1.2695325499835235, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 30.03650915601554, | |
| "count": 15674, | |
| "self": 9.969247708017974, | |
| "children": { | |
| "TorchPolicy.sample_actions": { | |
| "total": 20.067261447997566, | |
| "count": 15674, | |
| "self": 20.067261447997566 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.22179035300280248, | |
| "count": 15708, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 497.3854300300019, | |
| "count": 15708, | |
| "is_parallel": true, | |
| "self": 252.28970552599753, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.005047757999932401, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0037834449998399577, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001264313000092443, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001264313000092443 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.050933747000044605, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005918800000017654, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005456559999856836, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005456559999856836 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04787152100004732, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04787152100004732 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0019246900000098321, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005081189998463742, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001416571000163458, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001416571000163458 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 245.09572450400435, | |
| "count": 15707, | |
| "is_parallel": true, | |
| "self": 7.156004362004182, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 6.069965124005989, | |
| "count": 15707, | |
| "is_parallel": true, | |
| "self": 6.069965124005989 | |
| }, | |
| "communicator.exchange": { | |
| "total": 207.88473008700532, | |
| "count": 15707, | |
| "is_parallel": true, | |
| "self": 207.88473008700532 | |
| }, | |
| "steps_from_proto": { | |
| "total": 23.985024930988857, | |
| "count": 15707, | |
| "is_parallel": true, | |
| "self": 6.12303310196387, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 17.861991829024987, | |
| "count": 125656, | |
| "is_parallel": true, | |
| "self": 17.861991829024987 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 183.15117476201192, | |
| "count": 15708, | |
| "self": 0.592759306008702, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 41.06375867500287, | |
| "count": 15708, | |
| "self": 41.06375867500287 | |
| }, | |
| "_update_policy": { | |
| "total": 141.49465678100034, | |
| "count": 92, | |
| "self": 54.37541224799304, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 87.1192445330073, | |
| "count": 5745, | |
| "self": 87.1192445330073 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1739998626580928e-06, | |
| "count": 1, | |
| "self": 1.1739998626580928e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.10983485400015525, | |
| "count": 1, | |
| "self": 0.0016721680001410277, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.10816268600001422, | |
| "count": 1, | |
| "self": 0.10816268600001422 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |