Raghu Rajan

MDP Playground integration into bsuite

5

Hi @iosband and @yotam, Hope you're doing well! Following our discussions, I added MDP Playground experiments into bsuite for the following dimensions of MDP Playground: **Delay**, **Transition Noise**, **Reward Noise**,...

[Bug] Allow noop_max to be 0 and make ClipReward actually clip rewards

5

In [atari_wrappers.py](https://github.com/DLR-RM/stable-baselines3/blob/b8c72a53489c6d80196a1dc168835a2f375b868d/stable_baselines3/common/atari_wrappers.py), allow `noop_max` to be `0` to make it possible to have a completely deterministic Atari environment. Also in the same file, having `ClipRewardEnv` bin, and not clip rewards,...

https://github.com/automl/ConfigSpace/blob/cb4521ab0a61d3a7536d2309479bf3b3f6defda8/ConfigSpace/configuration_space.pyx#L527 https://github.com/automl/ConfigSpace/blob/cb4521ab0a61d3a7536d2309479bf3b3f6defda8/ConfigSpace/configuration_space.pyx#L331 https://github.com/automl/ConfigSpace/blob/cb4521ab0a61d3a7536d2309479bf3b3f6defda8/ConfigSpace/configuration_space.pyx#L336 https://github.com/automl/ConfigSpace/blob/cb4521ab0a61d3a7536d2309479bf3b3f6defda8/ConfigSpace/nx/classes/digraph.py#L424

[Feature Request] Training data selection: Create more "interesting" Replay Buffer Iterators

4

# 🚀 Feature Request Create Replay Buffer Iterators that can select training and validation data in various "interesting" ways, similar to `TransitionIterator` and `BootStrapIterator` in [https://github.com/facebookresearch/mbrl-lib/blob/b0aabd79941efe8b56bcabbd1b43bf497b9b1746/mbrl/replay_buffer.py](https://github.com/facebookresearch/mbrl-lib/blob/b0aabd79941efe8b56bcabbd1b43bf497b9b1746/mbrl/replay_buffer.py) Examples: 1) Select transitions...

check_shapes() updating l_x, α, l_y, β inside itself but the changes are not propagating to the original variables when it returns

2

Hi Jean, Thanks for the library! I hope your PhD thesis writing's going fine. I seem to have found an insidious bug. When we initialize measures as 2-D tensors with...

Create a new release/tag incorporating seed() update to ToGymEnv

1

Hi, Could you please create a new release/tag for the library? Specifically, we need incorporating the commit https://github.com/openai/gym3/commit/fe14d673246329ad9b6253c6c81b79f404ede0a8 because ProcGen uses gym3 as a dependency and when we use a...

Hi @Neeratyoy , I added the rank correlation plot functionality (basically the 4th plot from [here](https://automl.github.io/HpBandSter/build/html/auto_examples/plot_example_6_analysis.html)). Please let me know if it's fine to merge it into development. I can...