Picture for Yongyuan Liang

Yongyuan Liang

Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion

Add code
Jul 15, 2024
Viaarxiv icon

Is poisoning a real threat to LLM alignment? Maybe more so than you think

Add code
Jun 17, 2024
Viaarxiv icon

ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Add code
Feb 22, 2024
Figure 1 for ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Figure 2 for ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Figure 3 for ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Figure 4 for ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Viaarxiv icon

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Add code
Feb 20, 2024
Viaarxiv icon

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Add code
Feb 13, 2024
Viaarxiv icon

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Add code
Oct 30, 2023
Figure 1 for DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Figure 2 for DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Figure 3 for DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Figure 4 for DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Viaarxiv icon

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Add code
Jul 22, 2023
Figure 1 for Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Figure 2 for Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Figure 3 for Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Figure 4 for Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Viaarxiv icon

Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning

Add code
Oct 12, 2022
Figure 1 for Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Figure 2 for Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Figure 3 for Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Figure 4 for Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Viaarxiv icon

Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems

Add code
Jul 02, 2022
Figure 1 for Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Figure 2 for Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Figure 3 for Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Figure 4 for Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Viaarxiv icon

Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL

Add code
Jun 09, 2021
Figure 1 for Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Figure 2 for Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Figure 3 for Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Figure 4 for Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Viaarxiv icon