generalist/seed1: trained
Browse files- README.md +47 -9
- final.pt +3 -0
- run.json +67 -2
- train_metrics.csv +0 -0
- val_metrics.csv +12 -0
README.md
CHANGED
|
@@ -13,9 +13,9 @@ tags:
|
|
| 13 |
|
| 14 |
# racingmania-generalist-seed1
|
| 15 |
|
| 16 |
-
**Generalist (PPO)**, seed 1:
|
| 17 |
|
| 18 |
-
Status: **
|
| 19 |
|
| 20 |
RacingMania is an original 3D time-attack racing game for the browser (three.js + cannon-es `RaycastVehicle`) with reinforcement-learning drivers trained on a batched PyTorch port of the same car physics. Code, paper and full results: <https://github.com/BurnyCoder/reinforcement-learning-in-trackmania-like-racing-game>.
|
| 21 |
|
|
@@ -26,12 +26,12 @@ RacingMania is an original 3D time-attack racing game for the browser (three.js
|
|
| 26 |
| Algorithm | PPO |
|
| 27 |
| Architecture | MLP 2x256 tanh (actor and critic), two 3-way heads |
|
| 28 |
| Objective | centreline progress |
|
| 29 |
-
| Observation | car state + look-ahead points
|
| 30 |
-
| Training data | generated
|
| 31 |
-
| Start states | standing + random centreline |
|
| 32 |
-
| Agent steps trained |
|
| 33 |
-
| Wall-clock hours |
|
| 34 |
-
| Git commit |
|
| 35 |
|
| 36 |
## Evaluation
|
| 37 |
|
|
@@ -73,7 +73,45 @@ To watch it drive, open the game (`web/index.html`, or the GitHub Pages site) an
|
|
| 73 |
|
| 74 |
## Training configuration (from run.json)
|
| 75 |
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
## Licence and citation
|
| 79 |
|
|
|
|
| 13 |
|
| 14 |
# racingmania-generalist-seed1
|
| 15 |
|
| 16 |
+
**Generalist (PPO)**, seed 1: Generalist PPO agent trained on the whole generated training pool
|
| 17 |
|
| 18 |
+
Status: **trained** (trained to its step budget, not yet evaluated); physics version v1; card generated 2026-11-14 from the result files.
|
| 19 |
|
| 20 |
RacingMania is an original 3D time-attack racing game for the browser (three.js + cannon-es `RaycastVehicle`) with reinforcement-learning drivers trained on a batched PyTorch port of the same car physics. Code, paper and full results: <https://github.com/BurnyCoder/reinforcement-learning-in-trackmania-like-racing-game>.
|
| 21 |
|
|
|
|
| 26 |
| Algorithm | PPO |
|
| 27 |
| Architecture | MLP 2x256 tanh (actor and critic), two 3-way heads |
|
| 28 |
| Objective | centreline progress |
|
| 29 |
+
| Observation | car state + 20 look-ahead points |
|
| 30 |
+
| Training data | 48,949 generated tracks |
|
| 31 |
+
| Start states | standing + random centreline (p=0.5) |
|
| 32 |
+
| Agent steps trained | 1,000,341,504 |
|
| 33 |
+
| Wall-clock hours | 1.92 |
|
| 34 |
+
| Git commit | `a861208dbcd896c0f7fe896657c5ee2ca2f45920` |
|
| 35 |
|
| 36 |
## Evaluation
|
| 37 |
|
|
|
|
| 73 |
|
| 74 |
## Training configuration (from run.json)
|
| 75 |
|
| 76 |
+
| Setting | Value |
|
| 77 |
+
|---|---|
|
| 78 |
+
| `total_steps` | `1000000000` |
|
| 79 |
+
| `num_envs` | `16384` |
|
| 80 |
+
| `num_steps` | `32` |
|
| 81 |
+
| `lr` | `0.001` |
|
| 82 |
+
| `adaptive_lr` | `True` |
|
| 83 |
+
| `desired_kl` | `0.01` |
|
| 84 |
+
| `lr_min` | `1e-05` |
|
| 85 |
+
| `lr_max` | `0.01` |
|
| 86 |
+
| `gamma` | `0.99` |
|
| 87 |
+
| `gae_lambda` | `0.95` |
|
| 88 |
+
| `num_minibatches` | `4` |
|
| 89 |
+
| `update_epochs` | `5` |
|
| 90 |
+
| `clip_coef` | `0.2` |
|
| 91 |
+
| `ent_coef` | `0.01` |
|
| 92 |
+
| `vf_coef` | `1.0` |
|
| 93 |
+
| `max_grad_norm` | `1.0` |
|
| 94 |
+
| `weight_decay` | `0.0` |
|
| 95 |
+
| `hidden` | `[256, 256]` |
|
| 96 |
+
| `action_mode` | `factored` |
|
| 97 |
+
| `eval_every_minutes` | `10.0` |
|
| 98 |
+
| `checkpoint_every_minutes` | `10.0` |
|
| 99 |
+
| `rotate_tracks_every` | `20` |
|
| 100 |
+
| `loaded_tracks` | `4096` |
|
| 101 |
+
| `seed` | `1` |
|
| 102 |
+
| `compile` | `True` |
|
| 103 |
+
| `env.random_start_prob` | `0.5` |
|
| 104 |
+
| `env.random_start_speed` | `[0.0, 30.0]` |
|
| 105 |
+
| `env.random_start_lateral` | `0.5` |
|
| 106 |
+
| `env.max_steps` | `1500` |
|
| 107 |
+
| `env.reward_scale` | `0.1` |
|
| 108 |
+
| `env.window_k` | `20` |
|
| 109 |
+
| `env.window_stride` | `3` |
|
| 110 |
+
| `env.blind` | `False` |
|
| 111 |
+
| `env.time_cost` | `0.0` |
|
| 112 |
+
| `env.fall_penalty` | `0.0` |
|
| 113 |
+
| `env.hint_weight` | `0.0` |
|
| 114 |
+
| `env.scripted_starts` | `False` |
|
| 115 |
|
| 116 |
## Licence and citation
|
| 117 |
|
final.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863cbbb64bf8db342ebd20fddb226f7851a2053e3ad6c6a9898b40c89d1b59e5
|
| 3 |
+
size 870476
|
run.json
CHANGED
|
@@ -2,7 +2,72 @@
|
|
| 2 |
"experiment": "generalist",
|
| 3 |
"seed": 1,
|
| 4 |
"track": null,
|
| 5 |
-
"status": "
|
| 6 |
"phase": "2-single-seed",
|
| 7 |
-
"updated": "2026-11-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 2 |
"experiment": "generalist",
|
| 3 |
"seed": 1,
|
| 4 |
"track": null,
|
| 5 |
+
"status": "trained",
|
| 6 |
"phase": "2-single-seed",
|
| 7 |
+
"updated": "2026-11-14T13:52:46.891775+00:00",
|
| 8 |
+
"algo": "ppo",
|
| 9 |
+
"description": "Generalist PPO agent trained on the whole generated training pool",
|
| 10 |
+
"git_commit": "a861208dbcd896c0f7fe896657c5ee2ca2f45920",
|
| 11 |
+
"physics": "v1",
|
| 12 |
+
"hardware": {
|
| 13 |
+
"platform": "Linux-6.18.58.1-microsoft-standard-WSL2-x86_64-with-glibc2.39",
|
| 14 |
+
"python": "3.13.18",
|
| 15 |
+
"torch": "2.15.0+cu132",
|
| 16 |
+
"gpu": "NVIDIA GeForce RTX 5070 Laptop GPU"
|
| 17 |
+
},
|
| 18 |
+
"ppo": {
|
| 19 |
+
"total_steps": 1000000000,
|
| 20 |
+
"num_envs": 16384,
|
| 21 |
+
"num_steps": 32,
|
| 22 |
+
"lr": 0.001,
|
| 23 |
+
"adaptive_lr": true,
|
| 24 |
+
"desired_kl": 0.01,
|
| 25 |
+
"lr_min": 1e-05,
|
| 26 |
+
"lr_max": 0.01,
|
| 27 |
+
"gamma": 0.99,
|
| 28 |
+
"gae_lambda": 0.95,
|
| 29 |
+
"num_minibatches": 4,
|
| 30 |
+
"update_epochs": 5,
|
| 31 |
+
"clip_coef": 0.2,
|
| 32 |
+
"ent_coef": 0.01,
|
| 33 |
+
"vf_coef": 1.0,
|
| 34 |
+
"max_grad_norm": 1.0,
|
| 35 |
+
"weight_decay": 0.0,
|
| 36 |
+
"hidden": [
|
| 37 |
+
256,
|
| 38 |
+
256
|
| 39 |
+
],
|
| 40 |
+
"action_mode": "factored",
|
| 41 |
+
"eval_every_minutes": 10.0,
|
| 42 |
+
"checkpoint_every_minutes": 10.0,
|
| 43 |
+
"rotate_tracks_every": 20,
|
| 44 |
+
"loaded_tracks": 4096,
|
| 45 |
+
"seed": 1,
|
| 46 |
+
"compile": true
|
| 47 |
+
},
|
| 48 |
+
"env": {
|
| 49 |
+
"random_start_prob": 0.5,
|
| 50 |
+
"random_start_speed": [
|
| 51 |
+
0.0,
|
| 52 |
+
30.0
|
| 53 |
+
],
|
| 54 |
+
"random_start_lateral": 0.5,
|
| 55 |
+
"max_steps": 1500,
|
| 56 |
+
"reward_scale": 0.1,
|
| 57 |
+
"window_k": 20,
|
| 58 |
+
"window_stride": 3,
|
| 59 |
+
"blind": false,
|
| 60 |
+
"time_cost": 0.0,
|
| 61 |
+
"fall_penalty": 0.0,
|
| 62 |
+
"hint_weight": 0.0,
|
| 63 |
+
"scripted_starts": false
|
| 64 |
+
},
|
| 65 |
+
"n_train_tracks": 48949,
|
| 66 |
+
"vehicle_overrides": {},
|
| 67 |
+
"checkpoint_dir": "/mnt/d/AI/racingmania/checkpoints/generalist/seed1",
|
| 68 |
+
"tensorboard_dir": "/mnt/d/AI/racingmania/tensorboard/generalist/seed1",
|
| 69 |
+
"global_step": 1000341504,
|
| 70 |
+
"iterations": 1908,
|
| 71 |
+
"wall_hours": 1.9208961590131124,
|
| 72 |
+
"last_session_hours": 1.921039325926039
|
| 73 |
}
|
train_metrics.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
val_metrics.csv
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
sws,finish_rate,speed_ratio_finished,n_tracks,flags_overspeed,flags_energy_gain,iteration,global_step,wall_hours
|
| 2 |
+
0.0,0.0,nan,197,0,0,0,0,0.0
|
| 3 |
+
1.0633366484118099,0.7055837563451777,1.5070310772455147,197,0,0,190,99614720,0.16784764839543237
|
| 4 |
+
1.222279800802202,0.8071065989847716,1.5143969858995834,197,0,0,447,234356736,0.34694840570290886
|
| 5 |
+
1.235236382031222,0.8223350253807107,1.5021084398774736,197,0,0,649,340262912,0.5273539512024985
|
| 6 |
+
1.2149324516693405,0.8071065989847716,1.5052936665337109,197,0,0,845,443023360,0.704637470708953
|
| 7 |
+
1.2137514569703414,0.8071065989847716,1.503830421529291,197,0,0,1004,526385152,0.8858941390779284
|
| 8 |
+
1.2266359276614214,0.817258883248731,1.5009147686291928,197,0,1,1163,609746944,1.0669237690501743
|
| 9 |
+
1.2469413931465156,0.8324873096446701,1.497850332011363,197,0,0,1306,684720128,1.2468739506271151
|
| 10 |
+
1.2210377541718485,0.817258883248731,1.4940648296388455,197,0,0,1450,760217600,1.4269774105813768
|
| 11 |
+
1.2547547272829231,0.8578680203045685,1.4626430844658924,197,0,0,1594,835715072,1.6063099728027979
|
| 12 |
+
1.221571630943686,0.8121827411167513,1.5040600705994134,197,0,0,1798,942669824,1.785360698832406
|