pytorch rl issues - Githubissues

pytorch / rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

https://pytorch.org/rl

MIT License

2k stars 268 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Feature Request] multi-turn reward for RLHF

#2271 vmoens opened 2 hours ago
0
Fixed shape for MultiStep returns + Distributional loss

#2270 roger-creus opened 12 hours ago
3
[Feature Request] Support for distributional-DQNalgorithms (C51, Rainbow)

#2269 roger-creus opened 1 day ago
2
Fix "Run in Colab" and "Download Notebook" links in tutorials

#2268 kurtamohler closed 1 day ago
1
[Versioning] v0.5 bump

#2267 vmoens opened 2 days ago
3
[Quality] Fix low/high in SOTA implementations

#2266 vmoens closed 2 days ago
3
[BUG] A2C fails with functional=True and shifted=True for ValueEstimator

#2265 jkrude opened 3 days ago
5
[BUG] Error reloading a non-initialised buffer

#2264 matteobettini opened 3 days ago
5
[WIP] Correct typos

#2263 vmoens opened 4 days ago
3
[BugFix] Fix non-tensor passage in _StepMDP

#2262 vmoens closed 4 days ago
3
Revert "[BugFix] Fix non-tensor passage in _StepMDP"

#2261 vmoens closed 4 days ago
3
[BugFix] Fix non-tensor passage in _StepMDP

#2260 vmoens closed 4 days ago
3
[Doc] Add Custom Options for VideoRecorder

#2259 N00bcak closed 1 day ago
4
[Feature Request] Allow custom video settings to be passed into `CSVExperiment.add_video`

#2258 N00bcak opened 4 days ago
0
[BUG] `EnvBase.step_and_maybe_reset(td)` modifies the ('next','observation') data too on partial reset with`NonTensorStack`

#2257 jkrude closed 4 days ago
1
[Refactor] Remove `_run_checks` from `TensorDict.__init__`

#2256 vmoens closed 5 days ago
1
[Doc] Edit README for local installs

#2255 vmoens closed 1 week ago
3
[Question] Only Windows distribution when version>=2024.6.24

#2254 wertyuilife2 closed 2 days ago
1
[Quality] Warn if the sampler is not prioritized but update_priority is called

#2253 vmoens closed 1 week ago
3
[BugFix] Fix update_priority generic signature for Samplers

#2252 vmoens closed 1 week ago
3
[Feature] Some improvements to VecNorm

#2251 vmoens closed 1 week ago
3
[CI] Bump jinja2 from 3.1.3 to 3.1.4 in /docs

#2250 dependabot[bot] closed 1 week ago
3
[Algorithm] TD3+BC

#2249 BY571 opened 1 week ago
1
[CI] Upgrade SDL to install pygame 2.6

#2248 vmoens closed 1 week ago
3
[Feature] ActionDiscretizer

#2247 vmoens closed 1 week ago
3
[WIP] AlphaZero

#2246 vmoens opened 1 week ago
3
[CI] Fix CI

#2245 vmoens closed 1 week ago
3
[BugFix] Fix and test PRB priority update across dims and rb types

#2244 vmoens closed 1 week ago
1
[BugFix] Fix max value within buffer during update priority

#2242 vmoens closed 2 weeks ago
1
[BugFix] Fix typo in weight assignment in PRB

#2241 vmoens closed 2 weeks ago
3
[BugFix] Fix collector tests where device ordinal is needed

#2240 vmoens closed 2 weeks ago
3
[BugFix] Fix OOB sampling in PrioritizedSliceSampler

#2239 vmoens closed 2 weeks ago
3
Switch maybe_dense_stack calls from TensorDict to LazyStackedTensorDict

#2238 c3-utsavdutta98 opened 2 weeks ago
3
[Feature] _make_ordinal_device

#2237 vmoens closed 2 weeks ago
3
[BUG] `check_env_specs` + `PixelRenderTransform` does not tolerate "cuda" device

#2236 N00bcak closed 2 weeks ago
0
[Bug] With `MultiSyncDataCollector`, `tensors` cannot be instantiated on CUDA in child processes.

#2235 N00bcak opened 2 weeks ago
2
[BUG/QUESTION] Dimensionality Problem with Basic Module Setup despite successful check_env_specs

#2234 jako5 closed 2 weeks ago
2
[BugFix] Fix Brax

#2233 vmoens closed 2 weeks ago
3
[BugFix] Fix collectors with non tensors

#2232 vmoens closed 2 weeks ago
3
[Performance] consolidate TDs in ParallelEnv without buffers

#2231 vmoens closed 1 week ago
3
[BUG] Unexpected behavior of SumSegmentTree Resulting in Invalid Slices in PrioritizedSliceSampler.sample()

#2230 wertyuilife2 closed 2 weeks ago
3
[BugFix] Fix sliced PRB when only traj is provided

#2228 vmoens closed 3 weeks ago
4
[Feature] Add require gradient into reward

#2227 taindp98 opened 3 weeks ago
2
[BugFix] Fix prefetch in samples without replacement - .sample() compatibility issues

#2226 vmoens closed 3 weeks ago
3
[BugFix] Fix slice sampler end computation at the cursor place

#2225 vmoens closed 3 weeks ago
3
[Feature] assinging values to RB storage

#2224 vmoens closed 3 weeks ago
3
[Quality] better error message for CompositeSpec shape mismatch

#2223 vmoens closed 3 weeks ago
3
Not knowing Which key is causing shape mismatch

#2222 aminrezaee closed 3 weeks ago
3
[Performance, Refactor, BugFix] Faster loading of uninitialized storages

#2221 vmoens closed 3 weeks ago
4
[Feature] Make ProbabilisticActor compatible with Composite distributions

#2220 vmoens closed 3 weeks ago
3