rl icon indicating copy to clipboard operation
rl copied to clipboard

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

Results 254 rl issues
Sort by recently updated
recently updated
newest added

## Motivation It would be nice to have a conda package (under the official [PyTorch channel](https://anaconda.org/pytorch/repo)) for `torchrl` for those of us that prefer to use conda for managing package...

enhancement

## Description - Added an `action_interp` parameter to enable or disable the action interpolation feature. - Added an `action_interp_buffer` attribute to store the previous action for interpolation. ## Motivation and...

enhancement
CLA Signed

Requested via https://discuss.pytorch.org/t/feature-request-consistent-dropout-implementation/183778 Implements https://arxiv.org/abs/2202.11818

enhancement
CLA Signed

## Description Added implementation of TQC algorithm. I've tried to stay as close to the original PyTorch implementation as possible. - Implementation is based on the implementation of SAC in...

CLA Signed
new algo

## Motivation Since in the original [PER paper](https://arxiv.org/abs/1511.05952) the parameter beta is changing its value during the training, it would be desirable to be able to perform similar experiments with...

enhancement

Nice benchmark to have as it would interact with other torch libraries http://arxiv.org/abs/2004.13649

enhancement
new algo

## Describe the bug When using `autocast`` in dreamer example, there is a RuntimeError: `` RuntimeError: masked_scatter_: expected self and source to have same dtypes but gotHalf and Float ``...

bug

## Describe the bug ``ObservationNorm`` with fixed ``obs_norm_state_dict`` is used in dreamer example, and this ``obs_norm_state_dict`` is estimated by only `cfg.init_env_steps` steps rollout. When the observation is ``pixels``, some pixels...

bug

## Motivation Want to add the MIMIC Dataset, generally used for Sepsis Treatment for benchmarking Batch-RL algorithms in a easy & efficient way. This dataset is used in many BatchRL...

enhancement

## Motivation A feature request regarding the `FrameSkipTransform` ([documentation here](https://pytorch.org/rl/reference/generated/torchrl.envs.transforms.FrameSkipTransform.html#torchrl.envs.transforms.FrameSkipTransform)). When the `frame_skip` parameter is set to an integer greater than 1, i.e. `frame_skip = 2`, and I do a...

enhancement