sheeprl

sheeprl copied to clipboard

DreamerV3: Hardware Resources Underutilized?

1

Hi, when I run (DreamerV3) experiments, especially ones with a replay_ratio > 1.0, training takes quite a long time. During these runs, my hardware resources are not being used much...

defrag-bambino

Handle for 2D/3D observations that are images

6

I was also about to open an issue regarding Dreamer on feature-vector based (partially observable) environments where no Cnn is needed (and as a matter of fact, to also handle...

belerico

updates: - [github.com/PyCQA/autoflake: v2.2.1 → v2.3.1](https://github.com/PyCQA/autoflake/compare/v2.2.1...v2.3.1) - [github.com/psf/black: 23.12.1 → 24.8.0](https://github.com/psf/black/compare/23.12.1...24.8.0) - [github.com/astral-sh/ruff-pre-commit: v0.1.11 → v0.6.8](https://github.com/astral-sh/ruff-pre-commit/compare/v0.1.11...v0.6.8)

pre-commit-ci[bot]

dv3 Imagination notebook re-visited

4

I can't find a button to reopen the issue, regarding #272, I have two questions! 1) shouldn't initial `stochastic_state` be flattened s.t. ``` stochastic_state = player.stochastic_state.view(1, 1, -1).clone() ``` in...

anthony0727

New Dreamer V3 manuscript

2

Hi! Sharing slight change in Dreamer V3 according to their updated(2024/04/17) manuscript https://arxiv.org/pdf/2301.04104 Also their codes are updated few hours ago https://github.com/danijar/dreamerv3 It includes change in the optimizer (LaProp), experiments...

anthony0727

ReplayBuffer storing actions size mismatch during env reset

7

Hi, I am trying to write a simple gym wrapper for an existing env. During testing, I am not facing the following issue: ``` File "/home/drt/miniconda3/envs/sheeprl/lib/python3.10/site-packages/sheeprl/algos/dreamer_v3/dreamer_v3.py", line 647, in main...

defrag-bambino

enabling self play

4

hi, i tried out this project and it is one of the few that actually works off the shelf, thank you for your work. Is there a way to enable...

drblallo

Add Environment Wrapper Tests

3

It would be nice to add a test for the environment wrappers we have. Maybe, using the dummy envs, we could do a couple of iterations and check that the...

michele-milesi

Pure python training, evaluation and rollout documentation request.

5

Hi everyone, As a professional who has worked with a few RL frameworks in the past, I can confidently say that this is one of the cleanest, most user-friendly, and...

redzhepdx

Last `N` actions as `mlp_keys` encoder input for `dreamer_v3`

10

Hi, Working on an Atari environment wrapper with action input buffer with `len=N` that I want to feed as input to `mlp_keys`. Algo config: ```yaml algo: mlp_keys: encoder: [actions] ```...

geranim0