GA3C
GA3C copied to clipboard
NVlabs
Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.
./_train.sh: line 3: 3010 Segmentation fault (core dumped) python GA3C.py "$@" Does anybody get a segmentation problem like this?
The `undo_logger_setup()` method has been removed from the OpenAI Gym library ([openai/gym@4c460ba](https://github.com/openai/gym/commit/4c460ba6c8959dd8e0a03b13a1ca817da6d4074f)) as it no longer modifies the global logging configuration. As a result, GA3C no longer works with the...
Because of the use of the deprecated `gym.undo_logger_setup()` method (openai/gym@4c460ba), GA3C no longer works with the most recent versions. Using this method is no longer required as OpenAI Gym no...
With the newer version of scipy, they don't have resize() method. Replacing it with OpenCV resize method.
Hello! Why the ProcessAgent use Process while the ThreadTrainer use Thread? I wonder whether the ProcessAgent.py could use Thread instead of Process
Spell checked 'adjust' on line 38. Also 'propoerly' might need to be changed to 'property', ambiguous, same line. I'll check your spelling if you add support for multi-GPUs, thanks.
Hello! In file ThreadTrain.py x__ = np.concatenate((x__, x_)) As x_ may shorter than TMAX, should we conduct padding before concatenate?
Thank you for the easy to use and fast A3C implementation. I created a simple problem for rapid testing that rewards 0 on all steps except the terminal step, where...
