A Neurally Plausible Model Learns Successor Representations In Partially Observable Environments

Abstract

Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent's location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sensory information. Successor representations (SR) have been proposed as a middle-ground between model-based and model-free reinforcement learning strategies, allowing for fast value computation and rapid adaptation to changes in the reward function or goal locations. Indeed, recent studies suggest that features of neural responses are consistent with the SR framework. However, it is not clear how such representations might be learned and computed in partially observed, noisy environments. Here, we introduce a neurally plausible model using distributional successor features, which builds on the distributed distributional code for the representation and computation of uncerta

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvertes2019a

Related papers

• AKF-SR: Adaptive Kalman Filtering-based Successor Representation (2022)6.34
• A First-occupancy Representation For Reinforcement Learning (2021)0.00
• Successor Features Combine Elements Of Model-free And Model-based Reinforcement Learning (2019)0.00
• Successor Feature Sets: Generalizing Successor Representations Across Policies (2021)5.84
• Count-based Exploration With The Successor Representation (2018)13.17
• Distributional Successor Features Enable Zero-shot Policy Optimization (2024)0.00
• Successor Feature Representations (2021)0.00
• Discrete State-action Abstraction Via The Successor Representation (2022)0.00