The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
When processing similar frames in succession, we can take advantage of the locality of the convolution operation to reevaluate only portions of the image that changed from the previous frame.
We designed and implemented a CUDA port of the Atari Learning Environment (ALE), a system for developing and evaluating deep reinforcement algorithms using Atari games.
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.
Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years.
Our work is a simple extension of the paper "Exploration by Random Network Distillation".
Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment.
Surprisingly, we observe that the representation learned by the neural network can be used as a feature space for the width-based planner without degrading its performance, thus removing the requirement of pre-defined features for the planner.
With the representation learning problem simplified, we can perform experiments with significantly less computational expense.
Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment.