Firehose

Filtered to Papers, tagged “observation supervision” · clear filters

Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives

All People Companies Papers Podcasts Hacker News

Browse by tag

continual learning 31 reinforcement learning 10 language models 4 robotics 4 agents 3 large language models 3 recursive self-improvement 3 vision-language models 3

17 SEP 2026 · Paper

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

This paper explores whether supervising both agent actions and environment observations during reinforcement learning improves agent exploration and performance. Practitioners might care because it could lead to better initialization for reinforcement learning tasks.

reinforcement learning observation supervision action prediction policy initialization environment modeling