6 papers
CAP: Codebook-Aligned Prediction for Tokenized Robot Policies
Haoran Chen, Jingtian Ji, Samuel Wheeler +2
Action tokenization converts continuous robot actions into discrete symbols that can be modeled autoregressively. However, existing tokenizer-based policies typically ignore the to…
Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?
Haoran Chen, Jingtian Ji, Samuel Wheeler +2
Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuou…
Flow-based Policy Adaptation without Policy Updates
Luzhe Sun, Jingtian Ji, Haoran Chen +2
Foundation models and other policies trained on large and diverse datasets can endow robots with semantic and task knowledge that would be difficult to acquire from task-specific d…
Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization
Buqing Nie, Yangqing Fu, Jingtian Ji +1
Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different pertur…
Adversarial Constrained Policy Optimization: Improving Constrained Reinforcement Learning by Adapting Budgets
Jianmina Ma, Jingtian Ji, Yue Gao
Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement l…
Improve Robustness of Reinforcement Learning against Observation Perturbations via Lipschitz Policy Networks
Buqing Nie, Jingtian Ji, Yangqing Fu +1
Deep Reinforcement Learning (DRL) has achieved remarkable advances in sequential decision tasks. However, recent works have revealed that DRL agents are susceptible to slight pertu…