no code implementations • 15 Nov 2023 • Zichen Chen, Jianda Chen, Mitali Gaidhani, Ambuj Singh, Misha Sra
The explanation component includes a why-choose explanation, a why-not-choose explanation, and a set of reason-elements that underlie the LLM's decision.
1 code implementation • ICLR 2022 • Jianda Chen, Sinno Jialin Pan
How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem.
no code implementations • NeurIPS 2020 • Jianda Chen, Shangyu Chen, Sinno Jialin Pan
In this paper, we propose a deep reinforcement learning (DRL) based framework to efficiently perform runtime channel pruning on convolutional neural networks (CNNs).
no code implementations • 25 Sep 2019 • Haiyan Yin, Jianda Chen, Sinno Jialin Pan
First, we propose a new reasoning paradigm to infer the novelty for the partially observable states, which is built upon forward dynamics prediction.
no code implementations • 3 Jul 2017 • Haiyan Yin, Jianda Chen, Sinno Jialin Pan
In deep reinforcement learning (RL) tasks, an efficient exploration mechanism should be able to encourage an agent to take actions that lead to less frequent states which may yield higher accumulative future return.