Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use RjtDaga/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use RjtDaga/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="RjtDaga/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.15464802086353302, | |
| "min": 0.15208865702152252, | |
| "max": 1.447746992111206, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 4681.5048828125, | |
| "min": 4572.3935546875, | |
| "max": 43918.8515625, | |
| "count": 70 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2099997.0, | |
| "min": 29952.0, | |
| "max": 2099997.0, | |
| "count": 70 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2099997.0, | |
| "min": 29952.0, | |
| "max": 2099997.0, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.8779743313789368, | |
| "min": -0.09133218973875046, | |
| "max": 0.8807908892631531, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 266.0262145996094, | |
| "min": -21.91972541809082, | |
| "max": 266.879638671875, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.0010312356753274798, | |
| "min": -0.048813823610544205, | |
| "max": 0.29584255814552307, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 0.3124644160270691, | |
| "min": -13.228546142578125, | |
| "max": 71.00221252441406, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06789671442626664, | |
| "min": 0.06237706045586882, | |
| "max": 0.07469935835771528, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0184507163939998, | |
| "min": 0.47853736402854946, | |
| "max": 1.0511151281049629, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01397229525221822, | |
| "min": 0.0011194735100473587, | |
| "max": 0.017243694988787316, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2095844287832733, | |
| "min": 0.01083067054639088, | |
| "max": 0.24141172984302245, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 9.14747961750911e-05, | |
| "min": 9.14747961750911e-05, | |
| "max": 0.00029838354339596195, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0013721219426263665, | |
| "min": 0.0013234019588663332, | |
| "max": 0.003937499987500066, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.13049157555555557, | |
| "min": 0.13049157555555557, | |
| "max": 0.19946118095238097, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.9573736333333336, | |
| "min": 1.3897045333333333, | |
| "max": 2.812499933333334, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0030561083980000002, | |
| "min": 0.0030561083980000002, | |
| "max": 0.009946171977142856, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.04584162597, | |
| "min": 0.04420925330000001, | |
| "max": 0.13126874334, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.007838266901671886, | |
| "min": 0.007838266901671886, | |
| "max": 0.3783225119113922, | |
| "count": 70 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.11757400631904602, | |
| "min": 0.11240337789058685, | |
| "max": 2.6482574939727783, | |
| "count": 70 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 204.31788079470198, | |
| "min": 204.31788079470198, | |
| "max": 999.0, | |
| "count": 70 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30852.0, | |
| "min": 15984.0, | |
| "max": 32877.0, | |
| "count": 70 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.795966654419899, | |
| "min": -1.0000000521540642, | |
| "max": 1.795966654419899, | |
| "count": 70 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 269.39499816298485, | |
| "min": -32.000001668930054, | |
| "max": 269.39499816298485, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.795966654419899, | |
| "min": -1.0000000521540642, | |
| "max": 1.795966654419899, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 269.39499816298485, | |
| "min": -32.000001668930054, | |
| "max": 269.39499816298485, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.016608028944562345, | |
| "min": 0.016608028944562345, | |
| "max": 7.594298015348613, | |
| "count": 70 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.4912043416843517, | |
| "min": 2.4347147760536245, | |
| "max": 121.50876824557781, | |
| "count": 70 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 70 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 70 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1778020645", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn Pyramid_config.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training7 --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": "1778026030" | |
| }, | |
| "total": 5384.498611387, | |
| "count": 1, | |
| "self": 0.5699944039997717, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.027159633999872312, | |
| "count": 1, | |
| "self": 0.027159633999872312 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 5383.901457349, | |
| "count": 1, | |
| "self": 3.10527803003788, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.1855840859998352, | |
| "count": 1, | |
| "self": 2.1855840859998352 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 5378.424498258962, | |
| "count": 137427, | |
| "self": 3.2579512753527524, | |
| "children": { | |
| "env_step": { | |
| "total": 3911.6803043376967, | |
| "count": 137427, | |
| "self": 3570.4534252464828, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 339.2927588758039, | |
| "count": 137427, | |
| "self": 10.16435686189834, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 329.12840201390554, | |
| "count": 132088, | |
| "self": 329.12840201390554 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 1.9341202154100756, | |
| "count": 137427, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 5368.414132229047, | |
| "count": 137427, | |
| "is_parallel": true, | |
| "self": 2063.4673725861703, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0019167159998687566, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006855729989183601, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012311430009503965, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012311430009503965 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04922108999926422, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005244110006970004, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004313709996495163, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004313709996495163 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.0466639739997845, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0466639739997845 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016013339991332032, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00034207399858132703, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012592600005518761, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012592600005518761 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 3304.9467596428767, | |
| "count": 137426, | |
| "is_parallel": true, | |
| "self": 73.92650729145862, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 51.17766143331846, | |
| "count": 137426, | |
| "is_parallel": true, | |
| "self": 51.17766143331846 | |
| }, | |
| "communicator.exchange": { | |
| "total": 2941.586943826602, | |
| "count": 137426, | |
| "is_parallel": true, | |
| "self": 2941.586943826602 | |
| }, | |
| "steps_from_proto": { | |
| "total": 238.25564709149785, | |
| "count": 137426, | |
| "is_parallel": true, | |
| "self": 50.769247269652624, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 187.48639982184523, | |
| "count": 1099408, | |
| "is_parallel": true, | |
| "self": 187.48639982184523 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1463.4862426459122, | |
| "count": 137427, | |
| "self": 6.277975821887594, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 286.8040576080293, | |
| "count": 137427, | |
| "self": 286.4532238420288, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.3508337660005054, | |
| "count": 4, | |
| "self": 0.3508337660005054 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1170.4042092159953, | |
| "count": 974, | |
| "self": 645.8849269618449, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 524.5192822541503, | |
| "count": 48161, | |
| "self": 524.5192822541503 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.3139997463440523e-06, | |
| "count": 1, | |
| "self": 1.3139997463440523e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.18609566000122868, | |
| "count": 1, | |
| "self": 0.0033983670018642442, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.18269729299936444, | |
| "count": 1, | |
| "self": 0.18269729299936444 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |