How do you get the most out of your parameters in deep RL? 🤔
@johanobandoc Aaron Courville and i say:
✂️A Pruned Network is a Good Network!✂️
https://t.co/bVOnuauBSo
We demonstrate that gradual magnitude pruning yields *dramatic* improvements in RL agents!
1/12
In our latest #NeurIPS2023 paper, led by @johanobandoc and with @marcgbellemare , we uncover the "small batch effect" for online value-based agents.
In "Small batch deep reinforcement learning" we show that reducing batch size (and nothing else!) leads to big improvements!
1/13
fairly impressed by NVIDIA's latest self-driving capabilities: https://t.co/eYEvaHawD0 - this is one of the most promising efforts I've seen in a while. #SelfDrivingCars#nvidia
Robot perception algorithms convert data from cameras and sensors into something useful for decision making and planning physical actions. See how perception and adaptability enable varied, high-energy behaviors like parkour. https://t.co/UA7ieFFMlV
I’m very happy to share our paper, Revisiting Rainbow, accepted in the Deep RL workshop @Neurips_Conf. I’ve been working with @pcastr for a few months, and I wanted to share my story, and how this work came to be, in the hope it motivates others in similar situations to mine.