Farama-Foundation/D4RL

View on GitHub

A collection of reference environments for offline reinforcement learning

Stars: 1.7k
Forks: 309
Open beginner issues: 0
Indexed issues: 99

Dominant language: Python
License: Apache-2.0
Last GitHub push: Nov 18, 2024
Latest indexed: Sep 15, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

99 open issues indexed

Discrepancy between results reported in CQL and D4rl papers Open

Farama-Foundation/D4RL#47 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Backward error when running BEAR Open

Farama-Foundation/D4RL#57 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
How can I visualize the action? Open

Farama-Foundation/D4RL#60 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
carla-town-v0 Open

Farama-Foundation/D4RL#61 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Carla env and dataset issue Open

Farama-Foundation/D4RL#66 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Failed to import flow Open

Farama-Foundation/D4RL#67 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Unable to run antmaze_sac.py nor antmaze_sac_rlkit.py Open

Farama-Foundation/D4RL#68 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
In MuJoCo dataset, how can we figure out the beginning of each episode? Open

Farama-Foundation/D4RL#73 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
can not install Open

Farama-Foundation/D4RL#80 · 12 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Propensities of logging policy available? Open

Farama-Foundation/D4RL#82 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Ways to recover trajectories in dataset Open

Farama-Foundation/D4RL#93 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Failed to load XML file: C:\Users\Administrator\AppData\Local\Temp\tmpw7b_qxyo.xml. Open

Farama-Foundation/D4RL#98 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
A single terminal flag in half cheetah environment Open

Farama-Foundation/D4RL#107 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Support for PyBullet Simulator Envionrment Open

Farama-Foundation/D4RL#108 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Comparison between algorithms Open

Farama-Foundation/D4RL#111 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
What is task-specific debugging "infos" for kitchen environment? Open

Farama-Foundation/D4RL#112 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
*** AttributeError: 'HopperEnv' object has no attribute 'get_dataset' Open

Farama-Foundation/D4RL#113 · 3 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Normalizing scores for different versions Open

Farama-Foundation/D4RL#114 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Mujoco version used in the dataset collection Open

Farama-Foundation/D4RL#115 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Updating Dataset Reproducibility Guide with mujoco environment versions Open

Farama-Foundation/D4RL#116 · 0 comments · 3 reactions · 0 assignees · Indexed Sep 15, 2026
Medium Policy Open

Farama-Foundation/D4RL#119 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Missing bullet-maze2d with dense rewards Open

Farama-Foundation/D4RL#120 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
copy i copy mujoco200 as mujoco200_linux, and there exist both mujoco200 and mujoco200_linux under ~/.mujoco/ directory. Open

Farama-Foundation/D4RL#122 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Could not find a version that satisfies the requirement dm-control (unavailable) (from d4rl) Open

Farama-Foundation/D4RL#123 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
How to calculate the average return of the D4RL dataset? Open

Farama-Foundation/D4RL#124 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Current breakage of install due to not specifying dm_control version (or versions for any dependency) Open

Farama-Foundation/D4RL#125 · 6 comments · 3 reactions · 0 assignees · Indexed Sep 15, 2026
download the datasets with get_dataset() method Open

Farama-Foundation/D4RL#127 · 0 comments · 3 reactions · 0 assignees · Indexed Sep 15, 2026
What are the differences between the different versions of gym-mujoco? Open

Farama-Foundation/D4RL#131 · 0 comments · 3 reactions · 0 assignees · Indexed Sep 15, 2026
Building wheel for pybullet (setup.py) ... error Open

Farama-Foundation/D4RL#133 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
dataset generation for custom environment Open

Farama-Foundation/D4RL#134 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
error: No registered env, when use gym.make Open

Farama-Foundation/D4RL#135 · 5 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Training Mujoco-Gym Tasks with Image Observations Open

Farama-Foundation/D4RL#136 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Recovering trajectories for the Androit environments Open

Farama-Foundation/D4RL#137 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
import d4rl Cannot find MuJoCo library issue Open

Farama-Foundation/D4RL#139 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
I can't use maze environments Open

Farama-Foundation/D4RL#140 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
when installing dm_control error: Header file 'mjdata.h' does not exist. Open

Farama-Foundation/D4RL#141 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Contact forces are zero in Ant-v2 dataset Open

Farama-Foundation/D4RL#143 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
import d4rl error Open

Farama-Foundation/D4RL#144 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
problem of qlearning_dataset Open

Farama-Foundation/D4RL#145 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Installation issue related to mjrl Open

Farama-Foundation/D4RL#147 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Question about Maximum Score and Expert Dataset Open

Farama-Foundation/D4RL#151 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Truncated image returned by env.render("rgb_array"). Open

Farama-Foundation/D4RL#154 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Requirement to build wheel ... error Open

Farama-Foundation/D4RL#155 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Step-by-step instalation tutorial? Open

Farama-Foundation/D4RL#156 · 2 comments · 6 reactions · 0 assignees · Indexed Sep 15, 2026
possible to get a whole expert trajectory? Open

Farama-Foundation/D4RL#157 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Maze2d rewards seem odd? Open

Farama-Foundation/D4RL#158 · 3 comments · 2 reactions · 0 assignees · Indexed Sep 15, 2026
Issues with generating ant maze dataset Open

Farama-Foundation/D4RL#164 · 4 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026
Migrate to use the dm_control (or mujoco Python binding) Open

Farama-Foundation/D4RL#166 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
[Question] Adding new tasks Open

Farama-Foundation/D4RL#169 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
[Question] Reproducing qpos and qvel Open

Farama-Foundation/D4RL#172 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Farama-Foundation/D4RL

Get new issues in your inbox