Search Results for author:
Found 3 papers, 1 papers with code
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct Preference Optimization (DPO).
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
A crucial limitation of this framework is that every policy in the pool is optimized w. r. t.
Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward
These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
