Search Results for author:
Found 7 papers, 3 papers with code
Task Aware Dreamer for Task Generalization in Reinforcement Learning
Extensive experiments in both image-based and state-based tasks show that TAD can significantly improve the performance of handling different tasks simultaneously, especially for those with high TDR, and display a strong generalization ability to unseen tasks.
On the Reuse Bias in Off-Policy Reinforcement Learning
In this paper, we reveal that the instability is also related to a new notion of Reuse Bias of IS -- the bias in off-policy evaluation caused by the reuse of the replay buffer for evaluation and optimization.
Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
Among different adversarial noises, universal adversarial perturbations (UAP), i. e., a constant image-agnostic perturbation applied on every input frame of the agent, play a critical role in Embodied Vision Navigation since they are computation-efficient and application-practical during the attack.
Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation.
Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning
In this paper, we provide a framework to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space.
Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty caused by stochastic policies and environment variability.
Strategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents
Deep reinforcement learning (DRL) policies are vulnerable to the adversarial attack on their observations, which may mislead real-world RL agents to catastrophic failures.
