Super-mario-bros-A3C-pytorch
Super-mario-bros-A3C-pytorch copied to clipboard
uvipen
Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros
Hi, when I try to run this code using CUDA I always am getting this error. It works fine on CPU and other programs work fine using CUDA. I tried...
I want some Higher resolution videos because the quality of the output is too low. Is that any way to output video with a higher resolution?
Sorry, I refered to google but still confused about the GlabalAdam optimizer. Can someone give me a HELP?? ```py for group in self.param_groups: for p in group['params']: state = self.state[p]...
Training process 0 terminated The code runs for 80688.54 s Exception in thread Thread-1: Traceback (most recent call last): File "/home/anaconda3/envs/mario/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "/home/anaconda3/envs/mario/lib/python3.6/site-packages/tensorboardX/event_file_writer.py", line 202,...
Hi, I am wondering why there is no break statement in the local_test in this script [https://github.com/uvipen/Super-mario-bros-A3C-pytorch/blob/master/src/process.py]. It seems like the testing loop will run forever. How to terminate the...
When I interrupted my last training, How should I continue my training? Otherwise, once I start training, I can't stop.
https://github.com/uvipen/Super-mario-bros-A3C-pytorch/blob/004d331c5f16022dfcf5d62d10574a7737db0bca/train.py#L49 In the first convolution layer in model.py, you specify the input channels as num_inputs. After digging through your repo, you're calling `create_train_env()` in `src/env.py` For Atari environments, breakout/pong/space-force, the...
Hi, When i training with your code, (my global steps option is 5k,) Process 0. Episode 99 Training process 5 terminated The code runs for 95.45s Training process 1 terminated...
