A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
B-pref: Bench- marking preference-based reinforcement learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
SENIOR improves feedback efficiency and policy learning speed in PbRL by combining motion-distinction query selection via kernel density estimation with preference-guided intrinsic rewards, showing gains on simulated and real robot tasks.
VLM-AR3L learns absolute and relative reward models from VLM preference labels to improve RL on control, manipulation, and Minecraft tasks.
citing papers explorer
-
Implicit Safety Alignment from Crowd Preferences
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
-
SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
SENIOR improves feedback efficiency and policy learning speed in PbRL by combining motion-distinction query selection via kernel density estimation with preference-guided intrinsic rewards, showing gains on simulated and real robot tasks.
-
VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning
VLM-AR3L learns absolute and relative reward models from VLM preference labels to improve RL on control, manipulation, and Minecraft tasks.