Chen Gong (University of Vriginia), Kecen Li (Chinese Academy of Sciences), Jin Yao (University of Virginia), Tianhao Wang (University of Virginia)

Reinforcement learning (RL) trains an agent from experiences interacting with the environment. In scenarios where online interactions are impractical, offline RL, which trains the agent using pre-collected datasets, has become popular. While this new paradigm presents remarkable effectiveness across various real-world domains, like healthcare and energy management, there is a growing demand to enable agents to rapidly and completely eliminate the influence of specific trajectories from both the training dataset and the trained agents. To meet this problem, this paper advocates TRAJDELETER, the first practical approach to trajectory unlearning for offline RL agents. The key idea of TRAJDELETER is to guide the agent to demonstrate deteriorating performance when it encounters states associated with unlearning trajectories. Simultaneously, it ensures the agent maintains its original performance level when facing other remaining trajectories. Additionally, we introduce TRAJAUDITOR, a simple yet efficient method to evaluate whether TRAJDELETER successfully eliminates the specific trajectories of influence from the offline RL agent. Extensive experiments conducted on six offline RL algorithms and three tasks demonstrate that TRAJDELETER requires only about 1.5% of the time needed for retraining from scratch. It effectively unlearns an average of 94.8% of the targeted trajectories yet still performs well in actual environment interactions after unlearning. The replication package and agent parameters are available.

View More Papers

IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems

Yuhao Wu (Washington University in St. Louis), Franziska Roesner (University of Washington), Tadayoshi Kohno (University of Washington), Ning Zhang (Washington University in St. Louis), Umar Iqbal (Washington University in St. Louis)

Read More

ICSQuartz: Scan Cycle-Aware and Vendor-Agnostic Fuzzing for Industrial Control...

Corban Villa (New York University Abu Dhabi), Constantine Doumanidis (New York University Abu Dhabi), Hithem Lamri (New York University Abu Dhabi), Prashant Hari Narayan Rajput (InterSystems), Michail Maniatakos (New York University Abu Dhabi)

Read More

Query Privacy in Data Spaces

Shuwen Liu (School of Data Science, The Chinese University of Hong Kong, Shenzhen, China), George C. Polyzos (School of Data Science, The Chinese University of Hong Kong, Shenzhen, China and ExcID P.C., Athens, Greece)

Read More

Vision: Retiring Scenarios — Enabling Ecologically Valid Measurement in...

Oliver D. Reithmaier (Leibniz University Hannover), Thorsten Thiel (Atmina Solutions), Anne Vonderheide (Leibniz University Hannover), Markus Dürmuth (Leibniz University Hannover)

Read More