Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization
This work addresses the challenge of efficient intuitive physics learning for AI agents, though it is incremental as it builds on existing deep reinforcement learning and graphical network methods.
The paper tackles the problem of learning intuitive physics models by integrating a graphical physics network with deep reinforcement learning, using intrinsic reward normalization to guide agent interactions, and shows improved action diversity and model accuracy in 3D physics simulations.
At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive physics. Human infants learn and develop these models, which later serve as prior knowledge for further learning. Inspired by such behaviors exhibited by human infants, we introduce a graphical physics network integrated with deep reinforcement learning. Specifically, we introduce an intrinsic reward normalization method that allows our agent to efficiently choose actions that can improve its intuitive physics model the most. Using a 3D physics engine, we show that our graphical physics network is able to infer object's positions and velocities very effectively, and our deep reinforcement learning network encourages an agent to improve its model by making it continuously interact with objects only using intrinsic motivation. We experiment our model in both stationary and non-stationary state problems and show benefits of our approach in terms of the number of different actions the agent performs and the accuracy of agent's intuition model. Videos are at https://www.youtube.com/watch?v=pDbByp91r3M&t=2s