oyster

oyster copied to clipboard

The code seems not working well with mujoco-200

1

I've install mujoco-200 following the instruction, and I run "python launch_experiment.py ./configs/cheetah-dir.json". It should work as it is mentioned in Readme("For the task distributions in which the reward function varies...

Cubism-star

Discrete action_space

6

Hi katerakelly, thank you very much for sharing the code for your paper. I think your approach is very promising. Now, I am trying to implement your method to my...

songanz

Failed to fetch https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/Packages.gz Hash Sum mismatch

2

When I was running` Docker build.-t Pearl`, I encountered the following error: ``` Sending build context to Docker daemon 16.9kB Step 1/35 : ARG UBUNTU_VERSION=16.04 Step 2/35 : ARG ARCH=...

zhuliwen

fix typo

chungshan

Typos in simple_replay_buffer.py ?

1

Is this a typo ? should you change episode_starts => _episode_starts https://github.com/katerakelly/oyster/blob/3a4777b95e1772a74142c49a33b5ca1db768d140/rlkit/data_management/simple_replay_buffer.py#L79

duongnhatthang

Error when config recurrent encoder

1

I run the cheetah-vel experiment, only changing the recurrent encoder to True. I got the error: collecting initial pool of data for train and eval Traceback (most recent call last):...

duongnhatthang

It seems you used pytorch 1.0.1 in your project. Pytorch has added inplace detection since 1.5 which makes your code ```python def get_action(self, obs, deterministic=False): ''' sample action from the...

Lagrant

I checked the DockerHub Mujoco Repository. The website that it referred to - to collect the MujoCo license is down now and is not working. Is there any other way...

Satwik290896

Thanks for sharing the repo! I was wondering where can I change the experiment seed? I can't seem to find seed in launch_experiment.py or default_config or env specific config file.

SapanaChaudhary

modified: rlkit/core/rl_algorithm.py By adding `self.agent.clear_z()` after https://github.com/katerakelly/oyster/blob/44e20fddf181d8ca3852bdf9b6927d6b8c6f48fc/rlkit/core/rl_algorithm.py#L419 RNN hidden state will be reset and corresponds to the one task set in the [`evaluate` fun](https://github.com/katerakelly/oyster/blob/44e20fddf181d8ca3852bdf9b6927d6b8c6f48fc/rlkit/core/rl_algorithm.py#L397). modified: launch_experiment.py I add two click.option,...

CeyaoZhang