A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games

By Felix Leibfried, Nate Kushman, Katja Hofmann. 2016

45 citations recorded by the source corpus.

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment. In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating that it is possible to learn system dynamics and the reward structure jointly. Our contribution is to extend a recently developed deep neural network for video frame prediction in Atari games to enable reward prediction as well. To this end, we phrase a joint optimization problem for minimizing both video frame and reward reconstruction loss, and adapt network parameters accordingly. Empirical evaluations on five Atari games demonstrate accurate cumulative reward prediction of up to 200 frames. We consider these results as opening up important directions for model-based reinforcement learning in complex, initially unknown environments.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Model-Based Reinforcement Learning for Atari (2019, background): “ugh prior works have proposed training predictive models for next-frame, future-frame, as well as combined future-frame and reward predictions in Atari games (Oh et al. (2015); Chiappa et al. (2017); Leibfried et al. (2016)), no prior work has successfully demonstrated model-based control via predic”
Imagination-Augmented Agents for Deep Reinforcement Learning (2017, methodology): “In this work, we will consider in particular environment models that build on recent successes of action-conditional next-step predictors [17–19], which receive as input the current observation (or history of observations) and current action, and predict the next observation, and potentially the…”
Transparency in Deep Reinforcement Learning Networks (2018, background): “[22] for simultaneous next state and reward prediction.”
Model-Based Stabilisation of Deep Reinforcement Learning (2018, background): “Gradients are clipped when exceeding a norm of 1.0 (Leibfried, Kushman, and Hofmann 2017).”
Do recent advancements in model-based deep reinforcement learning really improve data efficiency? (2019, background): “Both non-perfect models followed standard architecture for the task (Oh et al., 2015; Leibfried et al., 2016).”