|
|
8a078fb59e
|
Fix: Issue with env wrapping (ensure batch dim)
|
2024-11-07 11:39:09 +01:00 |
|
|
|
e927afcc30
|
Extend policy impl
|
2024-10-21 15:24:20 +02:00 |
|
|
|
ca1ee980ef
|
Fix: Bug in loss calc for TRPLLoss
|
2024-10-21 15:23:57 +02:00 |
|
|
|
0c6e58634f
|
Rework algo impls
|
2024-10-21 15:23:39 +02:00 |
|
|
|
651ef1522f
|
Fixing issues with projections
|
2024-10-21 15:23:17 +02:00 |
|
|
|
71cb8593d9
|
Fix: Tried to reference gym space classes even if no gym avaible
|
2024-08-30 08:05:41 +02:00 |
|
|
|
54bab221ef
|
Disable vlearn for now...
|
2024-08-28 11:55:43 +02:00 |
|
|
|
1a02568f3c
|
Rename frob_projection file
|
2024-08-28 11:55:30 +02:00 |
|
|
|
ebff2551cd
|
projections_legacy no longer requierd
|
2024-08-28 11:34:26 +02:00 |
|
|
|
9c55b6a110
|
remove old vleasrn objective impl
|
2024-08-28 11:33:30 +02:00 |
|
|
|
4f58ce0ff2
|
refactor algo impls
|
2024-08-28 11:33:20 +02:00 |
|
|
|
dd98af9f77
|
Refactor objective losses
|
2024-08-28 11:32:51 +02:00 |
|
|
|
25988bab54
|
Added tmp (untested) vlearn objective impl
|
2024-08-28 11:32:22 +02:00 |
|
|
|
cb48badcff
|
Adapt init
|
2024-08-28 11:32:07 +02:00 |
|
|
|
5fc4b30ea8
|
New projection impls
|
2024-08-28 11:31:42 +02:00 |
|
|
|
416c2036a5
|
vlearn loss draft
|
2024-07-17 14:53:11 +02:00 |
|
|
|
e106d8701f
|
Vlearn draft
|
2024-07-17 14:52:44 +02:00 |
|
|
|
5f279beccf
|
New proj implementations
|
2024-07-17 14:51:59 +02:00 |
|
|
|
8d5d44e992
|
Refactor out some func into general Algo class
|
2024-06-02 16:36:59 +02:00 |
|
|
|
5f186af9fb
|
Fix class name for TRPL
|
2024-06-02 16:25:18 +02:00 |
|
|
|
7861821d0d
|
Worked on TRPL module
|
2024-06-02 14:14:12 +02:00 |
|
|
|
65c6a950aa
|
Use loggers correclty
|
2024-06-02 14:13:36 +02:00 |
|
|
|
4091df45f5
|
Implement rudimentary TerminalLogger
|
2024-06-02 14:12:41 +02:00 |
|
|
|
c7f5fcbf0f
|
I hate debugging tensordict weirdness
|
2024-06-02 13:56:54 +02:00 |
|
|
|
a867a74138
|
Reorder...
|
2024-06-02 12:09:26 +02:00 |
|
|
|
d51bf948d4
|
Make sure we work without original gym installed
|
2024-06-02 12:09:13 +02:00 |
|
|
|
78d79cf705
|
Initial code fro projections
|
2024-06-02 11:57:19 +02:00 |
|
|
|
add8e92b4a
|
Add norms
|
2024-06-02 11:52:20 +02:00 |
|
|
|
c6a12aa27b
|
Started TRPL impl
|
2024-06-02 11:49:09 +02:00 |
|
|
|
3931f5e31b
|
Started implementation of TRPL loss objective module
|
2024-06-02 11:48:51 +02:00 |
|
|
|
b34224f189
|
refactor dir structure
|
2024-06-02 11:13:04 +02:00 |
|
|
|
0a95ea652a
|
Support for torchrl envs
|
2024-06-02 11:11:18 +02:00 |
|
|
|
50733bb1a4
|
Make use of new utils to work with any space
|
2024-06-02 11:07:57 +02:00 |
|
|
|
59060c7533
|
refactor
|
2024-06-02 11:07:46 +02:00 |
|
|
|
a3cca71ac9
|
Add utils to handle all known space types
|
2024-06-02 11:06:55 +02:00 |
|
|
|
015f1e256a
|
Refactor
|
2024-05-31 18:25:03 +02:00 |
|
|
|
bd507c37c3
|
native support for fancy_gym
|
2024-05-31 13:11:09 +02:00 |
|
|
|
1d8d217ec0
|
Refactor env handling
|
2024-05-31 13:04:41 +02:00 |
|
|
|
1d1d9060f9
|
Switch to using torchrl loggers
|
2024-05-31 13:04:26 +02:00 |
|
|
|
7ea0bdcec6
|
Remove utils.py
|
2024-05-31 13:04:02 +02:00 |
|
|
|
8946362336
|
Oh, I could start using git...
|
2024-05-29 21:21:43 +02:00 |
|
