Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information
cs.AI, cs.LG
Submitted: 2026-10-29
Updated: 2026-11-13
Comments: 11 pages, 1 figure. Accepted at the CoRL 2026 Workshop on Memory for Robot Foundation Models (https://corl2026-memory.github.io/)
Project page: https://corl2026-memory.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
- Mastering Diverse Domains through World Models
- Neural Turing Machines
- Lie Access Neural Turing Machine
- Neural Map: Structured Memory for Deep Reinforcement Learning
- Counterfactual Credit Assignment in Model-Free Reinforcement Learning
- Counterfactual Shapley Credit Assignment
- Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents