Research map / Reinforcement learning / MDPs and planning

Addressing Signal Delay in Deep Reinforcement Learning

ICLR 2024 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Formalizes delayed-observation MDPs for signal delay in DRL and proposes a method to address the delay, evaluated on continuous-control tasks.

Problem

Signal delay, the lag between an agent's perception of the environment and its actions, is overlooked in deep reinforcement learning and degrades performance.

Approach

Extends the standard MDP to a delayed-observation MDP (DOMDP) formalization and uses it as the basis for addressing signal delay in DRL agents.

Experimental setup

Builds on: Markov decision process

Closest papers by meaning

• Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays (NeurIPS 2025 · similarity 0.88)
• Delayed homomorphic reinforcement learning for environments with delayed feedback (NeurIPS 2026 · similarity 0.87)
• Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays (ICML 2024 · similarity 0.87)
• Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.86)
• Variational Delayed Policy Optimization (NeurIPS 2024 · similarity 0.86)
• Handling Delay in Real-Time Reinforcement Learning (ICLR 2025 · similarity 0.86)