Abstract: This paper proposes a value-based reinforcement learning (RL) framework for autonomously acquiring control policies using spiking neural networks (SNNs) for neurochip-driven edge robots. The ...
# Uncomment/comment one of the following blocks. # For 1T model, start with microbatch=1, try to get 2 and 4. If OOM w/ 4, use cpu-offloading # Set to cpu for ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results