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
|
2025-10-21 08:52:22 -07:00 |
|
lucidrains
|
15876d34cf
|
more muon prep
|
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
|
2025-10-20 12:42:27 -07:00 |
|
lucidrains
|
ca244a290c
|
first pass through the kv cache for the time block in the dynamics model
|
2025-10-20 12:25:50 -07:00 |
|
lucidrains
|
a7e0c395c3
|
allow for only rmsnorm for keys in attention
|
2025-10-20 11:20:49 -07:00 |
|
lucidrains
|
1345326656
|
another measure for the attending to nothing issue
|
2025-10-20 10:32:31 -07:00 |
|
lucidrains
|
55574c054e
|
assert
|
2025-10-19 09:59:42 -07:00 |
|
lucidrains
|
27ed6d0ba5
|
fix time kv cache
|
2025-10-19 09:16:06 -07:00 |
|
lucidrains
|
4930002e99
|
bit of progress on time kv cache
|
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)
|
2025-10-19 08:37:56 -07:00 |
|
lucidrains
|
f651d779e3
|
able to control the update of the loss ema from dynamics model forward
|
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
|
2025-10-19 08:24:41 -07:00 |
|
lucidrains
|
79a1b1c46e
|
oops
|
2025-10-18 10:31:48 -07:00 |
|
lucidrains
|
b6aa19f31e
|
complete multi-token prediction for actions, tackle loss balancing another day
|
2025-10-18 10:23:14 -07:00 |
|
lucidrains
|
bc629d78b1
|
inverse norm for continuous actions when sampling
|
2025-10-18 08:55:04 -07:00 |
|
lucidrains
|
0ee475d2df
|
oops
|
2025-10-18 08:50:53 -07:00 |
|
lucidrains
|
8c88a33d3b
|
complete multi token prediction for the reward head
|
2025-10-18 08:33:06 -07:00 |
|
lucidrains
|
911a1a8434
|
oops
|
2025-10-18 08:07:06 -07:00 |
|
lucidrains
|
83cfd2cd1b
|
task conditioning when dreaming
|
2025-10-18 07:47:13 -07:00 |
|
lucidrains
|
22e13c45fc
|
rename
|
2025-10-17 14:44:25 -07:00 |
|
lucidrains
|
c967404471
|
0.0.31
|
2025-10-17 08:55:42 -07:00 |
|
lucidrains
|
cb416c0d44
|
handle the entropies during policy optimization
|
2025-10-17 08:47:26 -07:00 |
|
lucidrains
|
61773c8219
|
eventually we will need to learn from the outside stream of experience
|
2025-10-17 08:06:24 -07:00 |
|
lucidrains
|
0dba734280
|
start the learning in dreams portion
|
2025-10-17 08:00:47 -07:00 |
|
lucidrains
|
a0161760a0
|
extract the log probs and predicted values (symexp two hot encoded) for the phase 3 RL training
|
2025-10-16 10:40:59 -07:00 |
|
lucidrains
|
2d20d0a6c1
|
able to roll out actions from one agent within the dreams of a world model
|
2025-10-16 10:15:43 -07:00 |
|
lucidrains
|
d74f09f0b3
|
a researcher in discord pointed out that the tokenizer also uses the axial space time transformer. redo without the 3d rotary and block causal, greatly simplifying the implementation
|
2025-10-16 09:40:14 -07:00 |
|
lucidrains
|
2ccb290e26
|
pass the attend kwargs for the block causal masking in tokenizer
|
2025-10-16 08:33:26 -07:00 |
|
lucidrains
|
517ef6b94b
|
oops
|
2025-10-16 07:03:51 -07:00 |
|
lucidrains
|
2a902eaaf7
|
allow reward tokens to be attended to as state optionally, DT-esque. figure out multi-agent scenario once i get around to it
|
2025-10-16 06:41:02 -07:00 |
|
lucidrains
|
d28251e9f9
|
another consideration before knocking out the RL logic
|
2025-10-14 11:10:26 -07:00 |
|
lucidrains
|
ff81dd761b
|
separate action and agent embeds
|
2025-10-13 11:36:21 -07:00 |
|
lucidrains
|
6dbdc3d7d8
|
correct a misunderstanding where past actions is a separate action token, while agent token is used for the prediction of next action, rewards, values
|
2025-10-12 16:16:18 -07:00 |
|
lucidrains
|
9c78962736
|
sampling actions
|
2025-10-12 11:27:12 -07:00 |
|
lucidrains
|
c5e64ff4ce
|
separate out the key from the value projections in attention for muon
|
2025-10-12 09:42:22 -07:00 |
|
lucidrains
|
ab5de6795f
|
bring in muon
|
2025-10-12 09:35:06 -07:00 |
|
lucidrains
|
8a73a27fc7
|
add nested tensor way for getting log prob of multiple discrete actions
|
2025-10-11 10:53:24 -07:00 |
|
lucidrains
|
01bf70e18a
|
0.0.14
|
2025-10-11 09:24:58 -07:00 |
|
lucidrains
|
563b269f8a
|
bring in hyper connections
|
2025-10-11 06:52:57 -07:00 |
|
lucidrains
|
5df3e69583
|
last commit for the day
|
2025-10-10 11:59:18 -07:00 |
|
lucidrains
|
9230267d34
|
handle subset of discrete action unembedding
|
2025-10-10 11:27:05 -07:00 |
|
lucidrains
|
32aa355e37
|
prepare unembedding parameters in ActionEmbedder as well as the policy head, to allow for behavioral cloning before RL
|
2025-10-10 10:41:48 -07:00 |
|
lucidrains
|
e2d86a4543
|
add a complete action embedder that can accept any number of discrete actions with variable bins as well as any number of continuous actions, pooled and added to the agent token as described in the paper (seems like they fixed that horrendous hack in dreamer v3 with sticky action)
|
2025-10-09 07:53:42 -07:00 |
|
lucidrains
|
4c2ed100a3
|
fix masking for multiple agent tokens
|
2025-10-08 08:26:44 -07:00 |
|
lucidrains
|
63b63dfedd
|
add shard
|
2025-10-08 06:56:03 -07:00 |
|
lucidrains
|
187edc1414
|
all set for generating the perceived rewards once the RL components fall into place
|
2025-10-08 06:33:28 -07:00 |
|
lucidrains
|
c056835aea
|
address https://github.com/lucidrains/dreamer4/issues/2
|
2025-10-08 05:55:22 -07:00 |
|
lucidrains
|
0fdb67bafa
|
add the noising of the latent context during generation, technique i think was from EPFL, or perhaps some google group that built on top of EPFL work
|
2025-10-07 09:37:37 -07:00 |
|