Hugging Face's logo

MattStammers
/
appo-atari_asteroid-superhuman

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Metrics Community
MattStammers commited on
Commit
e929685
·
1 Parent(s): 42fd5a6

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. .summary/0/events.out.tfevents.1697546584.rhmmedcatt-proliant-ml350-gen10 +3 -0
  3. .summary/1/events.out.tfevents.1697546584.rhmmedcatt-proliant-ml350-gen10 +3 -0
  4. README.md +2 -1
  5. checkpoint_p0/best_001117600_286105600_reward_1315.400.pth +3 -0
  6. checkpoint_p0/checkpoint_001145536_293257216.pth +3 -0
  7. checkpoint_p0/checkpoint_001146400_293478400.pth +3 -0
  8. checkpoint_p0/milestones/checkpoint_000017344_4440064.pth +3 -0
  9. checkpoint_p0/milestones/checkpoint_000031424_8044544.pth +3 -0
  10. checkpoint_p0/milestones/checkpoint_000045504_11649024.pth +3 -0
  11. checkpoint_p0/milestones/checkpoint_000059648_15269888.pth +3 -0
  12. checkpoint_p0/milestones/checkpoint_000073696_18866176.pth +3 -0
  13. checkpoint_p0/milestones/checkpoint_000087808_22478848.pth +3 -0
  14. checkpoint_p0/milestones/checkpoint_000101952_26099712.pth +3 -0
  15. checkpoint_p0/milestones/checkpoint_000116224_29753344.pth +3 -0
  16. checkpoint_p0/milestones/checkpoint_000130496_33406976.pth +3 -0
  17. checkpoint_p0/milestones/checkpoint_000144800_37068800.pth +3 -0
  18. checkpoint_p0/milestones/checkpoint_000159136_40738816.pth +3 -0
  19. checkpoint_p0/milestones/checkpoint_000173504_44417024.pth +3 -0
  20. checkpoint_p0/milestones/checkpoint_000187872_48095232.pth +3 -0
  21. checkpoint_p0/milestones/checkpoint_000202208_51765248.pth +3 -0
  22. checkpoint_p0/milestones/checkpoint_000216608_55451648.pth +3 -0
  23. checkpoint_p0/milestones/checkpoint_000230912_59113472.pth +3 -0
  24. checkpoint_p0/milestones/checkpoint_000245248_62783488.pth +3 -0
  25. checkpoint_p0/milestones/checkpoint_000259552_66445312.pth +3 -0
  26. checkpoint_p0/milestones/checkpoint_000273856_70107136.pth +3 -0
  27. checkpoint_p0/milestones/checkpoint_000288160_73768960.pth +3 -0
  28. checkpoint_p0/milestones/checkpoint_000302528_77447168.pth +3 -0
  29. checkpoint_p0/milestones/checkpoint_000316832_81108992.pth +3 -0
  30. checkpoint_p0/milestones/checkpoint_000331168_84779008.pth +3 -0
  31. checkpoint_p0/milestones/checkpoint_000345408_88424448.pth +3 -0
  32. checkpoint_p0/milestones/checkpoint_000359776_92102656.pth +3 -0
  33. checkpoint_p0/milestones/checkpoint_000374144_95780864.pth +3 -0
  34. checkpoint_p0/milestones/checkpoint_000388544_99467264.pth +3 -0
  35. checkpoint_p0/milestones/checkpoint_000402848_103129088.pth +3 -0
  36. checkpoint_p0/milestones/checkpoint_000417120_106782720.pth +3 -0
  37. checkpoint_p0/milestones/checkpoint_000431488_110460928.pth +3 -0
  38. checkpoint_p0/milestones/checkpoint_000445760_114114560.pth +3 -0
  39. checkpoint_p0/milestones/checkpoint_000460128_117792768.pth +3 -0
  40. checkpoint_p0/milestones/checkpoint_000474496_121470976.pth +3 -0
  41. checkpoint_p0/milestones/checkpoint_000488832_125140992.pth +3 -0
  42. checkpoint_p0/milestones/checkpoint_000503136_128802816.pth +3 -0
  43. checkpoint_p0/milestones/checkpoint_000517472_132472832.pth +3 -0
  44. checkpoint_p0/milestones/checkpoint_000531744_136126464.pth +3 -0
  45. checkpoint_p0/milestones/checkpoint_000546080_139796480.pth +3 -0
  46. checkpoint_p0/milestones/checkpoint_000560320_143441920.pth +3 -0
  47. checkpoint_p0/milestones/checkpoint_000574656_147111936.pth +3 -0
  48. checkpoint_p0/milestones/checkpoint_000588960_150773760.pth +3 -0
  49. checkpoint_p0/milestones/checkpoint_000603232_154427392.pth +3 -0
  50. checkpoint_p0/milestones/checkpoint_000617504_158081024.pth +3 -0
.gitattributes CHANGED
@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  git.diff filter=lfs diff=lfs merge=lfs -text
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  git.diff filter=lfs diff=lfs merge=lfs -text
37
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ sf_log.txt filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1697546584.rhmmedcatt-proliant-ml350-gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca679b85b37b196bcd04a0962b3e12a82267fd1a90c56c57ef279d41ad96a4a0
3
+ size 47071849
.summary/1/events.out.tfevents.1697546584.rhmmedcatt-proliant-ml350-gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e529c942378f50a418c3dd4d52a9f7cb3e7db405efe76c8d80a994d05771e9
3
+ size 24889961
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: atari_asteroid
16
  metrics:
17
  - type: mean_reward
18
- value: 1218.00 +/- 462.14
19
  name: mean_reward
20
  verified: false
21
  ---
@@ -24,6 +24,7 @@ model-index:
24
 
25
  This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist).
26
 
 
27
 
28
  ## Project Aims
29
 
 
15
  type: atari_asteroid
16
  metrics:
17
  - type: mean_reward
18
+ value: 225993.00 +/- 112245.84
19
  name: mean_reward
20
  verified: false
21
  ---
 
24
 
25
  This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist).
26
 
27
+ In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this.
28
 
29
  ## Project Aims
30
 
checkpoint_p0/best_001117600_286105600_reward_1315.400.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa8c9ad092341acf8945c2edb2db0f6df9b82cfb7c12638c1e54d63f847aaa4
3
+ size 20771187
checkpoint_p0/checkpoint_001145536_293257216.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90822f78d275766fcd5939a3c22fa700bbb01a9e8d106fc9980afc63b12acbb5
3
+ size 20771651
checkpoint_p0/checkpoint_001146400_293478400.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bef34215ef58e6e41a9984ea73e4e79a509eb7499b73bbd6fcd254b776c3d4
3
+ size 20771651
checkpoint_p0/milestones/checkpoint_000017344_4440064.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e101a2394d47e125bd7f2096783b784b614139d8cd08a9f03cf9322bcb94bdd
3
+ size 20772507
checkpoint_p0/milestones/checkpoint_000031424_8044544.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a0437495c34a5f9772784929973fdacd95a82a99f965c52992f7ff1e44c0e7
3
+ size 20772507
checkpoint_p0/milestones/checkpoint_000045504_11649024.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6005e88615cfcf024f34edb92ead07024970a747e98a8c0252fdd0f48c9e1527
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000059648_15269888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044a336b4fd5a63c184b40d0e87e1e4b68cf530bf93d3c0fff11850fd73a7b59
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000073696_18866176.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce35bfc3bfc3645a2ad50c377ebcb69d5b391739498f3a4849406bd87d4342c8
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000087808_22478848.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2de14f7b2a0451f82f728c29ff19ee639a9660c4560f4213c6acdb9aeeb024
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000101952_26099712.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea933d8882803349f787e7ddca0bdfd26ad2823e2c0259ae012aefa568a120d3
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000116224_29753344.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb391a1069c5226abed3d57f3da0e177741be6b1c7bc34d40dc6af0810a58fc
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000130496_33406976.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37fdf618e00fc4877cc07957cd8e6ebeaf2b39755c267f5934589a12d629c2e7
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000144800_37068800.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b644fd25a139e991b47ce7d0d7a21329af1f8d03a5d59c47733885fbd18676
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000159136_40738816.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b933e100ff4eb9a8a5171d459ddd5b62ba3e453a8cabfbe367b6dd0d2521120
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000173504_44417024.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c5ebaed7b4997c5b56e708556f50c2addf0b28352d080e08f80d7dd563bab7
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000187872_48095232.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8d004205f3cebc5752d0bd436223063dca95108e2e65291adbe96c00bd283d
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000202208_51765248.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb40b8e1daa3793e525a2891ef69480a134c74fb72f98b1d8843594e9e636f0
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000216608_55451648.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5945a45fea6a11cc3baf802f20e29ddb7dfdbc4c81202b92f1e2dc07f7d92c4b
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000230912_59113472.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb20a4336d3c595434f6740be33cc6933702e360a6e024aa7ce5ec8973b83b97
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000245248_62783488.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071327ab7a0624276b85454c0969903817d89ff157523ec5a77225bfb60fabce
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000259552_66445312.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebcbf5053199bc8e75f4387b6d8d003f7e6d70b5c922ca473a49ed07d8d3124a
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000273856_70107136.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1baae4a4ffbf2570774fb89048800e592dc275b7074009b44001f541c1c86819
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000288160_73768960.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20b85d7cd7cdaab3111de30e600f1d09d35fe43a90dfa8e33409cdda591e1b3
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000302528_77447168.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79222a5ec60fe41bc1d9216b7c6434ae2f3eb6ce9b53ff6ad6703b2543d10ac
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000316832_81108992.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c573c402b6c2f4a09d33c6cd0d4a862a62a0a8b830cb13de5e145526cc635ff1
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000331168_84779008.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a696955e14c6bc2350c260d49e0ce1e1ef2636ce9530deeff2b2d5e193a918
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000345408_88424448.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f7f39212335d9c6381adbc1ca4c7819d96916520518994f8e5b81c3787b88f
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000359776_92102656.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79655a6da23a9c737bed5a5f909a0dd8b240555a48844bd874693c5b7b6b07f
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000374144_95780864.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a88cbd121b2b0fd808ff5baf58454b64d107021043d6087fa5df2f0cae41a5
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000388544_99467264.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d9a824166d33ec5e3e928b5ee712b52a535167ee8750bca5d88946a3d52aec
3
+ size 20772563
checkpoint_p0/milestones/checkpoint_000402848_103129088.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd67763646672873ec1d79b4746af6635ad3187c04a3fb62591b18efceceb78
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000417120_106782720.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1819c25cd923f4349956fc1a0cc1b70f2baf526226b332aa7fab8b53f377e3d8
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000431488_110460928.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e215e2d8028277f28ad794dfbe2b4267d2cde27588d9e3dad329c631cba0cadc
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000445760_114114560.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf8ca679b447e8fc6069488f4b4012b9f8c4787a2b30c63a3df425449b466c5
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000460128_117792768.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c84021872691c617e22658d38b5e8cb654c5ff54a325a07cea28e43f8dc5efc
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000474496_121470976.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4064e396f2ede028f14f292762d49043a89b0daa36787999be819a58b14a44fc
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000488832_125140992.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46db5cc970b768746e1441dd8734d1bd4425aa7a7969b0bf7f264c4fb036b95b
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000503136_128802816.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd0d003a672abc18f423a524731e74f5659e55252180d83041b876b4e02f9d9
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000517472_132472832.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220438a8384c32c2a6874603198f89edc2eab0c9f5f66f53c0ce19ed9977cded
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000531744_136126464.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a10a92a045e32c291ca7f746f4d3c362a0acec8627222b18f619e4dbdf572b
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000546080_139796480.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac690b4ae75c5d1d6d3b9b4805feed6028f690c74b8c069140bbf69ecbacab9
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000560320_143441920.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb0529a780707f6ffd4de7dc81567b16f4aa31753561ddd922cfece980f1de5
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000574656_147111936.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e0eef3825f235db75bf8c31c47637d91d5199f2aab23bc21b0540a0bd4cbd3
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000588960_150773760.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d3c92f6416e33b04e98200eaa6eac3f61461c942a49a72ff5b9f7104cc7920
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000603232_154427392.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eda89977159370337e7a0580e1891713a4cb80ba6e2234c58ce3af04d51a32f
3
+ size 20772619
checkpoint_p0/milestones/checkpoint_000617504_158081024.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354a74580251dc6bec99585805ebc1857da3dd1aa322f1088a4627191df990e4
3
+ size 20772619