Actor-critic with experience replay
Available items
No Items, yet!
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
Readme
ACER
Actor-critic with experience replay (ACER) [1]. Uses batch off-policy updates to improve stability. Trust region updates can be enabled with
--trust-region. Currently uses full trust region instead of "efficient" trust region (see issue #1).
Run with
python main.py. To run asynchronous advantage actor-critic (A3C) [2] (but with a Q-value head), use the
--on-policyoption.
Requirements
To install all dependencies with Anaconda run
conda env create -f environment.ymland use
source activate acerto activate the environment.
Results
Acknowledgements
References
[1] Sample Efficient Actor-Critic with Experience Replay
[2] Asynchronous Methods for Deep Reinforcement Learning