Julian Dierkes issues

Results 4 issues of


                                            Julian Dierkes

Unit wiped reward not considered for sparse reward in wipe environment

Hi, I am confused about the sparse reward signal of the table wipe environment. It says in the environment's reward function that: https://github.com/ARISE-Initiative/robosuite/blob/eb01e1ffa46f1af0a3aa3ac363d5e63097a6cbcc/robosuite/environments/manipulation/wipe.py#L294-L301 Hence, I suspect to get a reward...

Added Parameter to PPO for weighting value loss

I added a parameter to PPO for specifying the weight of the value loss. See issue #424

[BUG] Atari Breakout does not reset with episodic_live=True

## Describe the bug Atari Breakout does not reset with `env.reset()` when `episodic_live=True`. This can be observed, for example, by the number of lives decreasing even though no actual steps...

Number Training Steps for Baselines

Hi, I am currently working on reproducing the baseline that you are proposing as plots in the robosuite whitepaper for the Wipe environment. In your whitepaper your are writing: >...