MiniGrid

MiniGrid is a benchmark that contains a variety of discrete tasks used to evaluate exploration strategies in reinforcement learning.

Papers using MiniGrid (26)

Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning2025 · 3 citesCIG: Exploration via Conditional Information Gain2026ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning2025 · 1 citesBeyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning2026Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning2026Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs2025TransZero: Parallel Tree Expansion in MuZero using Transformer Networks2025Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors2025The Impact Of Intrinsic Rewards On Exploration In Reinforcement Learning2025 · 1 citesWorld Model Agents With Change-based Intrinsic Motivation2025D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based On Causal Discovery And Spurious Correlation Detection2025D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection2025DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning2025Adaptive Data Exploitation in Deep Reinforcement Learning2025Effective Exploration Based on the Structural Information Principles2024 · 3 citesFostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models2024Words as Beacons: Guiding RL Agents with High-Level Language Prompts2024Learning Successor Features the Simple Way2024Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models2024A Temporally Correlated Latent Exploration for Reinforcement Learning2024The impact of intrinsic rewards on exploration in Reinforcement Learning2025World Model Agents with Change-Based Intrinsic Motivation2025LLM-Guided Probabilistic Program Induction for POMDP Model Estimation2025MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward2025Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning2025A representational framework for learning and encoding structurally enriched trajectories in complex agent environments2025