7 papers · 1 filter
Learning Process Rewards via Success Visitation Matching for Efficient RL
Raymond Tsao, Andrew Wagenmaker, Sergey Levine
In many modern applications of reinforcement learning (RL), the natural reward for a task of interest is inherently sparse: a reward of 0 is given everywhere except when the task i…
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
Andrew Wagenmaker, Perry Dong, Raymond Tsao +2
Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinf…
Behavioral Exploration: Learning to Explore via In-Context Adaptation
Andrew Wagenmaker, Zhiyuan Zhou, Sergey Levine
Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to…
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Jifan Zhang, Lalit Jain, Yang Guo +9
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2.2 million captions, collected through crowdsourcing…
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
Andrew Wagenmaker, Kevin Huang, Liyiming Ke +3
In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy…
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
Haolin Liu, Artin Tajdini, Andrew Wagenmaker +1
In linear bandits, how can a learner effectively learn when facing corrupted rewards? While significant work has explored this question, a holistic understanding across different a…