Xingdong Zuo

Release code for Mars Navigation and Mujoco continuous control ?

9

Is it also ok to release the code for Mars Navigation dataset, models and particularly the one for continuous control via Mujoco simulator. Did you use OpenAI Gym for it...

[Feature request]: Auto Sync all files

1

It could be very convenient to add a functionality to automatically/periodically sync all files to linked cloud services (Dropbox, Google Drive etc.) Perhaps it could be a on-off switch under...

It would be nice to add a few more standard environments, such as following: - Maze: spawn robot (Ant/Humanoid/Point mass) and the objective is to reach the goal - Gather:...

e.g. ```python # only read through the raw file without importing any modules def _get_version(dirpath): var_name = '__version__' file_path = Path(dirpath)/'__init__.py' with open(file_path, 'r') as fp: for line in fp:...

Reference paper: Deep Reinforcement Learning at the Edge of the Statistical Precipice. Github repo: https://github.com/google-research/rliable

Sync. RL baselines by calling `agent.train()` and `agent.eval()` explicitly.

This will dramatically increase reusability and reduce boilerplate code. e.g. ```python snapshot_nn(net, ['total_parameters', 'trainable_parameters']) ``` Networks: - Total parameters: trainable parameters, un-trainable parameters - Extract the number of such parameters...

This will ease the checkpointing, we don't have to serialize and load the entire environment within the agent. The `env_spec` object has sufficient information to build the agent e.g. the...