Assur modules improve limited-data learning of planar mechanisms
Assur-derived features give a geometric-mean 1.8× sample-efficiency gain over flattened adjacency and position inputs.
Stories per day · 30 days
3 RSS
Relatedlanguage-agents2reinforcement-learning2alfworld1compositionality1cope1grpo1mechanism-design1planar-mechanisms1representation-learning1scienceworld1webshop1
6 stories, newest first · one card per story
Stories tagged #sample-efficiency
CoPE co-trains action forecasting with language-agent policies
On ScienceWorld the authors report up to 1.9 times and 2.0 times the sample efficiency of ECHO and GRPO.
Co-Evolving Acting and Forecasting for Language Agents
CoPE trains language agents to act and forecast future actions, improving benchmark scores and sample efficiency.
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
Least-Square Policy Distillation beats on-policy distillation baselines by 1.59 Avg@16 on math reasoning.
Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries
Groupoid-based RL discovers local, state-dependent symmetries during interaction, learning in a symmetry-reduced space and beating standard Q-learning efficiency.
Scaling Automatic Research Agents via World Models
WMRL replaces environment execution with a world model in RL, accelerating research-agent post-training 3-4x and letting 4B/9B agents beat 48B/120B open-weight agents.