D4RL

D4RL copied to clipboard

Truncated image returned by env.render("rgb_array").

1

Hi, When I create an environment ant maze, and I try to render it, the returned image is centered on the agent start position and the full environment is not...

hbonnavaud

If you are submitting a bug report, please fill in the following details and use the tag [bug]. **Describe the bug** The `check_envs.py` script always fails with `hammer-human-v0`. ``` Checking...

Seraphli

[Bug Report] AntMaze envs ignore seed parameters

1

Hello! Seems like there are some problems with AntMaze tasks in terms of setting seeds. The following code: ```Python3 import numpy as np import random import gym import d4rl np.random.seed(0);...

DT6A

### Proposal Add the following lines to the _maze_env.py_: `if not(next_rowcol in next_visit): next_visit.append(next_rowcol)` This should be added to the lines 338 and 339 respectively. ### Motivation In my experiments...

dgumenyuk

The observations in Antmaze is like[qpos, qvel]. But there is difference between dataset['observations'] and dataset['infos/qpos'], dataset['infos/qvel']. 

rainbow979

Updating and debugging sequence_dataset()

1

Hello, Thank you very much for this open project and resources. I am researching Imitation and inverse reinforcement learning. D4RL has been a lifesaver. The following code returns an error...

HesNobi

**Bug Description** the "relocate-human-v1" and "relocate-expert-v1" seems to have unrealistic ball position. **Code example** ```python import d4rl import gym env = gym.make('relocate-expert-v1') dataset = env.get_dataset() i = 0 while i...

Aequatio-Space

Roadmap for D4RL

4

Recently, the [Farama Foundation](https://farama.org/) has recently taken over D4RL and has several plans for maintaining D4RL. 1. Add a PyPI release 2. Remove environments of necessary imports and have D4RL...

pseudo-rnd-thoughts

Carla env and dataset issue

1

In the `__init__.py` file in the `carla` folder, the config for `carla-lane-render-v0` environment is wrong. The `entry_point` should be `d4rl.carla:CarlaObsEnv` instead of `d4rl.carla:CarlaDictEnv`; and the `dataset_url` should be the same...

yanlai00

**Describe the bug** In the `maze2d-XXXX-v1` datasets, `rewards[t]` equals whether `observations[t]` reaches the goal. However, according to `MazeEnv` code, it should equal to whether `next_observations[t]`, i.e., `observations[t+1]` reaches the goal....

ssnl