conftrace_

goal generalization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

value function approximator (1) multimodal encoder (1) alignment problem (1) power-seeking behavior (1) multimodal reward (1) return-conditioned policy (1) fine-tuning distribution (1) embedding vector (1) artificial general intelligence (1) natural language instruction (1)

Papers

The Alignment Problem from a Deep Learning Perspective ICLR 2024 Guide Your Agent with Adaptive Multimodal Rewards NeurIPS 2023 Universal Value Function Approximators ICML 2015