A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

by   Mingde Zhao, et al.

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state, in order to plan and to generalize better out-of-distribution. The agent's architecture uses a set representation and a bottleneck mechanism, forcing the number of entities to which the agent attends at each planning step to be small. In experiments with customized MiniGrid environments with different dynamics, we observe that the design allows agents to learn to plan effectively, by attending to the relevant objects, leading to better out-of-distribution generalization.


page 6

page 22


Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning

Model-based reinforcement learning is a framework in which an agent lear...

On the role of planning in model-based deep reinforcement learning

Model-based planning is often thought to be necessary for deep, careful ...

Generalization of Reinforcement Learners with Working and Episodic Memory

Memory is an important aspect of intelligence and plays a role in many d...

Projective simulation with generalization

The ability to generalize is an important feature of any intelligent age...

Planification par fusions incrémentales de graphes

In this paper, we introduce a generic and fresh model for distributed pl...

Selective Dyna-style Planning Under Limited Model Capacity

In model-based reinforcement learning, planning with an imperfect model ...

Please sign up or login with your details

Forgot password? Click here to reset