Search Results for author:
Found 5 papers, 3 papers with code
Human Alignment of Large Language Models through Online Preference Optimisation
Building on this equivalence, we introduce the IPO-MD algorithm that generates data with a mixture policy (between the online and reference policy) similarly as the general Nash-MD algorithm.
A General Theoretical Paradigm to Understand Learning from Human Preferences
In particular we derive a new general objective called $\Psi$PO for learning from human preferences that is expressed in terms of pairwise preferences and therefore bypasses both approximations.
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
These latent embeddings are themselves trained to be predictive of the aforementioned representations.
Agent57: Outperforming the Atari Human Benchmark
Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade.
Ranked #1 on
Atari Games
on Atari 2600 HERO
Never Give Up: Learning Directed Exploration Strategies
Our method doubles the performance of the base agent in all hard exploration in the Atari-57 suite while maintaining a very high score across the remaining games, obtaining a median human normalised score of 1344. 0%.
Ranked #7 on
Atari Games
on atari game
