Low Precision Policy Distillation With Application To Low-power, Real-time Sensation-cognition-action Loop With Neuromorphic Computing

Abstract

Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network provides a principled, practical way to train an RL agent. As an application, on 10 different ATARI games, we demonstrate real-time end-to-end game playing on low-power neuromorphic hardware by converting a sequence of game frames into discrete actions.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymckinstry2018low

Related papers

• Low-precision Reinforcement Learning: Running Soft Actor-critic In Half Precision (2021)0.00
• Automaton Distillation: Neuro-symbolic Transfer Learning For Deep Reinforcement Learning (2023)0.00
• "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
• Playing Atari With Six Neurons (2018)0.00
• Learning Quantized Continuous Controllers For Integer Hardware (2025)0.00
• Minimalistic Attacks: How Little It Takes To Fool A Deep Reinforcement Learning Policy (2019)0.00
• Model-based Reinforcement Learning For Atari (2019)0.00
• Practical Policy Distillation For Reinforcement Learning In Radio Access Networks (2025)0.00