cangozpi

Results 4 issues of cangozpi

Hi, I am using a laptop with only cpu available. I believe I have to modify the *.sh files as was specified in the repository's README. Problem is that I...

Hi, Is the reason for the following code modifying the actions for the breakout game is eliminating the NOOP action from the available set of actions that can be taken...

In the [RND paper](https://arxiv.org/pdf/1810.12894.pdf) on page 15, it mentions that extrinsic rewards are clipped in [-1,1]. But in the [official RND code](https://github.dev/openai/random-network-distillation) in atari_wrappers.py it clips extrinsic rewards using the...

Hi, I was going through your implementation for Direct Feedback Alignement (DFA). As far as I can understand, you used register_backward_hook function to send the global error (e) to individual...