-
https://github.com/rail-berkeley/softlearning/blob/46f14436f62465a02b99f431bbcf57a7fa0fd09d/softlearning/algorithms/sac.py#L254-L255
The implementation of the alpha loss seems to vary from the formul…
-
Examples of BIS that are not being pulled under the new code but used to be:
1. 285baacbdf8fda1de94b19282acd23e2
2. cdfa4c42f465a5a66871587c69fcfa34
3. 33a854e247155d590883b93bca53848a (though t…
-
Is it possible to have an alternative way of handling max_steps in continuing environments? As of now the terminal field is set to 'true' when the environment reaches the max_steps even though it's st…
-
Hi, after I installed using `pip install -e .`, I tried to run:
python train.py --env-name PongNoFrameskip-v4 --cuda
in `reinforcement-learning-algorithms/rl_algorithms/a2c` and I get the f…
ghost updated
3 years ago
-
**Is your feature request related to a problem? Please describe.**
The basic request is to be able to launch training through python that achieves the exact same functions as mlagents-learn from the …
-
Hi Reese @reese ,
Thank you so much for creating this plugin! 👏 I was trying to use this in my Gatsby site, and was unfortunately running into few internal errors from the plugin.
This is my…
-
Question: Has anyone made some implementations of evolutionary algorithms in the ml-agents simulation framework?
I am looking to implement it (in a situation where an RL agent seems to make little …
-
I'm wondering if SAC can be used with RNN or attention to process sequence of states and still work as expected.
I have a few questions:
1. Do you have any result using the RNN as the preprocessor m…
51616 updated
3 years ago
-
hello? is this relates to ERDL, ER-DQN, or the deepmind paper "statistics and samples in distributional reinforcement learning"?
if so, i'm quite curious, how to calculate the equation 7?
what I can…
ddlau updated
3 years ago
-
The original MetaWorld paper discusses the reward decisions as follows:
> Designing reward functions for Meta-World requires two major considerations. First, to guarantee
that our tasks are within t…