softqlearning

softqlearning copied to clipboard

Suboptimal policy

1

I'm trying SQL on a simple manipulator reaching task, the agent quickly learns to get to the vicinity of the goal but then the learning curve plateaus and the agent...

xli4217

Recording videos

2

Hi, how can I record videos for various Gym envs? Thanks!

SJTUGuofei

action distribution for estimating V

8

Hi, First of all, thanks for this inspiring work! In https://github.com/haarnoja/softqlearning/blob/59c0bbb7d665616f796ab101de65227c89ffd318/softqlearning/algorithms/sql.py#L164 it seems to me that action is sampled from uniform distribution when estimating `V_{soft}` . In Sec. 3.2. of...

immars

change to mujoco 1.5

1

We are currently encountering that mujoco 1.3 does not run on any newer OSX versions. https://github.com/openai/mujoco-py/issues/36 Are you planning on supporting 1.5 anytime soon?

Karsten1987

This PR resolves issues about running the provided code in Docker with rllab. The migration from rllab to garage appears to overlook Docker usages, thus it may be harder to...

j3soon