Publications (4)
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Haoran Tang, Rein Houthooft, Davis Foote +6
Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov d…
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
Leon Lang, Davis Foote, Stuart Russell +3
Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on…
AI Alignment with Changing and Influenceable Reward Functions
Micah Carroll, Davis Foote, Anand Siththaranjan +2
Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems th…
Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer
Kunal Nagpal, Davis Foote, Yun Liu +17
For prostate cancer patients, the Gleason score is one of the most important prognostic factors, potentially determining treatment independent of the stage. However, Gleason scorin…