lucidrains
|
d476fa7b14
|
able to store the agent embeddings during rollouts with imagination or environment, for efficient policy optimization (but will also allow for finetuning world model for the heads)
0.0.85
|
2025-10-28 09:02:26 -07:00 |
|
lucidrains
|
789f091c63
|
redo so that max timesteps is treated as truncation at the last timestep, then allow for accepting the truncation signal from the environment and reuse same logic
0.0.83
|
2025-10-28 08:04:48 -07:00 |
|
lucidrains
|
41ab83f691
|
fix mock
|
2025-10-27 10:47:24 -07:00 |
|
lucidrains
|
995b1f64e5
|
handle environments that return a terminate flag, also make sure episode lens are logged in vectorized env
0.0.82
|
2025-10-27 10:14:28 -07:00 |
|
lucidrains
|
fd1e87983b
|
quantile filter
|
2025-10-27 09:08:26 -07:00 |
|
lucidrains
|
fe79bfa951
|
optionally keep track of returns statistics and normalize with them before advantage
0.0.81
|
2025-10-27 09:02:08 -07:00 |
|
lucidrains
|
f808b1c1d2
|
oops
0.0.80
|
2025-10-27 08:34:22 -07:00 |
|
lucidrains
|
349a03acd7
|
redo so lens is always the episode length, including the bootstrap value timestep, and use is_truncated to mask out the bootstrap node from being learned on
0.0.79
|
2025-10-27 08:06:21 -07:00 |
|
lucidrains
|
59c458aea3
|
introduce an is_truncated field on Experience, and mask out rewards and values before calculating gae appropriately
0.0.78
|
2025-10-27 07:55:00 -07:00 |
|
lucidrains
|
fbfd59e42f
|
handle variable lengthed experiences when doing policy optimization
0.0.77
|
2025-10-27 06:09:09 -07:00 |
|
lucidrains
|
46432aee9b
|
fix an issue with bc
|
2025-10-25 12:30:08 -07:00 |
|
lucidrains
|
f97d9adc97
|
oops, forgot to add the view embedding for robotics
0.0.75
|
2025-10-25 11:39:06 -07:00 |
|
lucidrains
|
32cf142b4d
|
take another step for variable len experiences
0.0.74
|
2025-10-25 11:31:41 -07:00 |
|
lucidrains
|
1ed6a15cb0
|
fix tests
|
2025-10-25 11:13:22 -07:00 |
|
lucidrains
|
4d8f5613cc
|
start storing the experience lens
0.0.73
|
2025-10-25 10:55:47 -07:00 |
|
lucidrains
|
3d5617d769
|
take a step towards variable lengthed experiences during training
0.0.72
|
2025-10-25 10:45:34 -07:00 |
|
lucidrains
|
77a40e8701
|
validate that we can generate multiple video streams for robotics use-case
|
2025-10-25 09:23:07 -07:00 |
|
lucidrains
|
4ce82f34df
|
given the VAT paper, add multiple video streams (third person, wrist camera, etc), geared for robotics. need to manage an extra dimension for multiple viewpoints
0.0.71
|
2025-10-25 09:20:55 -07:00 |
|
lucidrains
|
a9b728c611
|
incorporate proprioception into the dynamics world model
0.0.70
|
2025-10-24 11:24:22 -07:00 |
|
lucidrains
|
35c1db4c7d
|
sketch of training from sim env
0.0.69
|
2025-10-24 09:13:09 -07:00 |
|
lucidrains
|
27ac05efb0
|
function for combining experiences
0.0.67
|
2025-10-24 08:00:10 -07:00 |
|
lucidrains
|
d0ffc6bfed
|
with or without signed advantage
0.0.66
|
2025-10-23 16:24:29 -07:00 |
|
lucidrains
|
fb3e026fe0
|
handle vectorized env
0.0.65
|
2025-10-22 11:19:44 -07:00 |
|
lucidrains
|
7ecc5d03e8
|
wire up the time kv cache when interacting with sim / env
0.0.62
|
2025-10-22 08:39:11 -07:00 |
|
lucidrains
|
d82debb7a6
|
first pass through gathering experience with a mock env for online rl
0.0.61
|
2025-10-22 08:32:46 -07:00 |
|
lucidrains
|
03b16a48f2
|
sketch out the dream trainer, seems like they only fine tune the heads
0.0.60
|
2025-10-22 06:41:10 -07:00 |
|
lucidrains
|
6f1a7a24ed
|
try to fix ci
|
2025-10-21 11:47:39 -07:00 |
|
lucidrains
|
e316499047
|
naming
|
2025-10-21 10:57:55 -07:00 |
|
lucidrains
|
40da985c6b
|
tweak bc trainer
0.0.59
|
2025-10-21 10:55:24 -07:00 |
|
lucidrains
|
2fc3b17149
|
take a gradient step with behavioral clone trainer, make sure it works with and without actions and rewards
0.0.57
|
2025-10-21 10:20:08 -07:00 |
|
lucidrains
|
283d59d75a
|
oops
|
2025-10-21 09:50:07 -07:00 |
|
lucidrains
|
4a5465eeb6
|
fix ci
|
2025-10-21 09:17:53 -07:00 |
|
lucidrains
|
b34128d3d0
|
make sure time kv cache can be passed back in during generation
0.0.55
|
2025-10-21 09:15:32 -07:00 |
|
lucidrains
|
7ba3988fb9
|
prepare a mock for interacting with online env
|
2025-10-21 09:03:20 -07:00 |
|
lucidrains
|
ea13d4fcab
|
take a gradient step with video tokenizer trainer
0.0.54
|
2025-10-21 08:52:22 -07:00 |
|
lucidrains
|
15876d34cf
|
more muon prep
0.0.53
|
2025-10-21 08:23:59 -07:00 |
|
lucidrains
|
b4763caff9
|
fix rotary embeddings in presence of kv caching
|
2025-10-21 07:10:21 -07:00 |
|
lucidrains
|
7195bbb196
|
oops
0.0.50
|
2025-10-20 12:42:27 -07:00 |
|
lucidrains
|
ca244a290c
|
first pass through the kv cache for the time block in the dynamics model
0.0.49
|
2025-10-20 12:25:50 -07:00 |
|
lucidrains
|
a7e0c395c3
|
allow for only rmsnorm for keys in attention
0.0.48
|
2025-10-20 11:20:49 -07:00 |
|
lucidrains
|
1345326656
|
another measure for the attending to nothing issue
0.0.47
|
2025-10-20 10:32:31 -07:00 |
|
lucidrains
|
55574c054e
|
assert
0.0.46
|
2025-10-19 09:59:42 -07:00 |
|
lucidrains
|
27ed6d0ba5
|
fix time kv cache
0.0.45
|
2025-10-19 09:16:06 -07:00 |
|
lucidrains
|
4930002e99
|
bit of progress on time kv cache
0.0.44
|
2025-10-19 09:04:26 -07:00 |
|
lucidrains
|
ecbe13efe8
|
allow for setting different loss weights for each MTP head (perhaps more weight on the next vs some far out prediction)
0.0.43
|
2025-10-19 08:37:56 -07:00 |
|
lucidrains
|
f651d779e3
|
able to control the update of the loss ema from dynamics model forward
0.0.42
|
2025-10-19 08:25:50 -07:00 |
|
lucidrains
|
374667d8a9
|
take care of the loss normalization mentioned at the end of the first paragraph of section 3
0.0.41
|
2025-10-19 08:24:41 -07:00 |
|
lucidrains
|
79a1b1c46e
|
oops
0.0.40
|
2025-10-18 10:31:48 -07:00 |
|
lucidrains
|
b6aa19f31e
|
complete multi-token prediction for actions, tackle loss balancing another day
0.0.38
|
2025-10-18 10:23:14 -07:00 |
|
lucidrains
|
bc629d78b1
|
inverse norm for continuous actions when sampling
0.0.37
|
2025-10-18 08:55:04 -07:00 |
|