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

arXiv: https://arxiv.org/abs/1611.07078 · HTML: https://mlsanity.com/paper/1611.07078/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2016.

## Built on by (most cited first, 9 of 9)

- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models](https://mlsanity.com/paper/2102.08291/) (2021)
- [VPTR: Efficient Transformers for Video Prediction](https://mlsanity.com/paper/2203.15836/) (2022)
- [Video Prediction by Efficient Transformers](https://mlsanity.com/paper/2212.06026/) (2022)
- [Visual Perspective Taking for Opponent Behavior Modeling](https://mlsanity.com/paper/2105.05145/) (2021)
- [OPEn: An Open-ended Physics Environment for Learning Without a Task](https://mlsanity.com/paper/2110.06912/) (2021)
- [Learning Shared Dynamics with Meta-World Models](https://mlsanity.com/paper/1811.01741/) (2018)
- [Planning with Expectation Models for Control](https://mlsanity.com/paper/2104.08543/) (2021)
- [Reward-Predictive Clustering](https://mlsanity.com/paper/2211.03281/) (2022)

## Abstract (arXiv)

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.