Comments (7)
Missed to include the versions:
0.4.0 1.26.2 3.10.13 (main, Sep 11 2023, 08:16:02) [Clang 14.0.6 ] darwin
from rl.
Yes unfortunately we deprecated the behaviour of stack
because that required loads of checks and also some surprising behaviours from time to time!
You can also change this by passing the contiguous=False argument to rollout
Note to self: we should make it so that contiguous=False
calls LazyStackedTensorDict.maybe_dense_stack
to get the "best" stack possible
from rl.
Ok thanks that's helpful! Also, I wonder if we could create dense stacks of the nonuniform shaped tensors by batching them as nested tensors instead?
from rl.
Yes we can do that, I don't think we have the util to stack things as nested tensors yet though
The main issue we'll be facing is that nested tensors can only be stacked along dim 0 and rollout stacks along the last+1 dim, so it will only work for non-batched envs
from rl.
I wonder if we encounter such data maybe we can automatically pad the data and return a padding mask along the dynamic dimensions. This can be the fallback when the contained tensors are nested tensors. If you think that's an option, I can look into implementing something like this after the NeurIPS deadline.
from rl.
Another option is to create the nested tensor along dim 0 but "lie" with tensordict and present it as a transposed version
we'll need to patch the get set etc
from rl.
Closing this as now contiguous=False
will do a best intention attempt to stack what can be stacked and return non-contiguous stacks everywhere else
from rl.
Related Issues (20)
- [BUG] BRAX: batch size issue HOT 5
- [BUG] Incorrect Calculation of Mode for TanhNormal Distribution HOT 8
- [BUG] `LazyTensorStorage` allocates storage on wrong device
- [BUG] outdated PrioritizedSliceSampler implementation HOT 3
- [BUG] Numerical Instability issues with `torchrl.modules.TanhNormal` HOT 5
- [BUG] Calling `to` fails on MultiDiscreteTensorSpec
- [BUG] Multiple Issues in Samplers and Buffers Affecting Stability and Expected Behavior HOT 6
- [BUG] Segmentation Fault in PrioritizedSliceSampler.sample() HOT 2
- [BUG] Device Error in PrioritizedSliceSampler.sample()
- [BUG] Unintended Cross-Trajectory Sampling in PrioritizedSliceSampler.sample() HOT 5
- [Feature Request] A Method to Modify ReplayBuffer In Place HOT 4
- [BUG] Inadequate Default Priority Design in PrioritizedSampler HOT 5
- [BUG] Double Initialization of Priority for New Samples in PrioritizedSampler HOT 1
- [BUG] Potential Thread Safety Issue with PrioritizedSliceSampler and Prefetching
- Not knowing Which key is causing shape mismatch HOT 3
- [BUG] Unexpected behavior of SumSegmentTree Resulting in Invalid Slices in PrioritizedSliceSampler.sample() HOT 3
- [BUG/QUESTION] Dimensionality Problem with Basic Module Setup despite successful check_env_specs HOT 2
- [Bug] With `MultiSyncDataCollector`, `tensors` cannot be instantiated on CUDA in child processes. HOT 2
- [BUG] `check_env_specs` + `PixelRenderTransform` does not tolerate "cuda" device
- [Question] Only Windows distribution when version>=2024.6.24 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rl.