R-AIF: Solving Sparse-reward Robotic Tasks From Pixels With Active Inference And World Models

Abstract

Although research has produced promising results demonstrating the utility of active inference (AIF) in Markov decision processes (MDPs), there is relatively less work that builds AIF models in the context of environments and problems that take the form of partially observable Markov decision processes (POMDPs). In POMDP scenarios, the agent must infer the unobserved environmental state from raw sensory observations, e.g., pixels in an image. Additionally, less work exists in examining the most difficult form of POMDP-centered control: continuous action space POMDPs under sparse reward signals. In this work, we address issues facing the AIF modeling paradigm by introducing novel prior preference learning techniques and self-revision schedules to help the agent excel in sparse-reward, continuous action, goal-based robotic control POMDP environments. Empirically, we show that our agents offer improved performance over state-of-the-art models in terms of cumulative rewards, relative stabi

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keynguyen2024r

Related papers

• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• Reward Maximisation Through Discrete Active Inference (2020)10.74
• Online Reinforcement Learning With Sparse Rewards Through An Active Inference Capsule (2021)0.00
• Active Inference In Hebbian Learning Networks (2023)0.00
• AXIOM: Learning To Play Games In Minutes With Expanding Object-centric Models (2025)0.00
• Deconstructing Deep Active Inference (2023)2.26
• Action Inference By Maximising Evidence: Zero-shot Imitation From Observation With World Models (2023)2.29
• Task-guided IRL In Pomdps That Scales (2022)2.26