CGAR: Critic Guided Action Redistribution in Reinforcement Leaning

Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resources. It's essential to alleviate such waste. As discussed in this paper, under the settings of the off-policy actor critic algorithms, we demonstrate that the critic can bring more expected discounted rewards than or at least equal to the actor. Thus, the Q value predicted by the critic is a better signal to redistribute the action originally sampled from the policy distribution predicted by the actor. This paper introduces the novel Critic Guided Action Redistribution (CGAR) algorithm and tests it on the OpenAI MuJoCo tasks. The experimental results demonstrate that our method improves the sample efficiency and achieves state-of-the-art performance. Our code can be found at https://github.com/tairanhuang/CGAR.

Adversarial Attacks for Embodied Agents

Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have mainly focused on static scenes; however, it remains unclear whether such attacks are effective against embodied agents, which could navigate and interact with a dynamic environment. In this work, we take the first step to study adversarial attacks for embodied agents. In particular, we generate spatiotemporal perturbations to form 3D adversarial examples, which exploit the interaction history in both the temporal and spatial dimensions. Regarding the temporal dimension, since agents make predictions based on historical observations, we develop a trajectory attention module to explore scene view contributions, which further help localize 3D objects appeared with the highest stimuli. By conciliating with clues from the temporal dimension, along the spatial dimension, we adversarially perturb the physical properties (e.g., texture and 3D shape) of the contextual objects that appeared in the most important scene views. Extensive experiments on the EQA-v1 dataset for several embodied tasks in both the white-box and black-box settings have been conducted, which demonstrate that our perturbations have strong attack and generalization abilities.