Minimal Recurrent Behavioral Memory for Imitation under Partial Observability

arXiv:2609.25757 · cs.LG, cs.IT, cs.RO, math.IT · Submitted 2026-09-22 · Read on arXiv

cs.LG, cs.IT, cs.RO, math.IT

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 46 pages, 10 figures. Code: https://github.com/XianyaoLi/DIACRITIC

Code: https://github.com/XianyaoLi/DIACRITIC

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 24× in this paper · explained in 2 episodes
• Accuracy — 21× in this paper · explained in 1 episode
• System Identification — 21× in this paper · explained in 3 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Quantization — 7× in this paper · explained in 12 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Agent Memory — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Homogeneity — 2× in this paper · explained in 2 episodes
• Inverse Problem — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Regret — 2× in this paper · explained in 3 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• External Validation — 1× in this paper · explained in 2 episodes
• Holonomy — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Training and Evaluating Diffusion Policies with Long Context Lengths
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
• Memory Lens: How Much Memory Does an Agent Use?
• Gated Memory Policy: In-Context Memorization and Adaptation
• The Myhill-Nerode Theorem for Bounded Interaction: Canonical Abstractions via Agent-Bounded Indistinguishability
• Memory Retrieval in Visuomotor Policies for Long-Horizon Robot Control
• The information bottleneck method
• Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
• Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation
• Compressing History into Memory: Distilling Transformers into Recurrent Transformers
• Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs
• What Must Generalist Agents Remember?
• Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes
• Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks