MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement learning agents. Much of the appeal comes from the fact that Atari games demonstrate aspects of competency we expect from an intelligent agent and are not biased toward any particular solution approach. The challenge of the ALE includes (1) the representation learning problem of extracting pertinent information from raw pixels, and (2) the behavioural learning problem of leveraging complex, delayed associations between actions and rewards. Often, the research questions we are interested in pertain more to the latter, but the representation learning problem adds significant computational expense. We introduce MinAtar, short for miniature Atari, a new set of environments that capture the general mechanics of specific Atari games while simplifying the representational complexity to focus more on the behavioural challenges. MinAtar consists of analogues of five Atari games: Seaquest, Breakout, Asterix, Freeway and Space Invaders. Each MinAtar environment provides the agent with a 10x10xn binary state representation. Each game plays out on a 10x10 grid with n channels corresponding to game-specific objects, such as ball, paddle and brick in the game Breakout. To investigate the behavioural challenges posed by MinAtar, we evaluated a smaller version of the DQN architecture as well as online actor-critic with eligibility traces. With the representation learning problem simplified, we can perform experiments with significantly less computational expense. In our experiments, we use the saved compute time to perform step-size parameter sweeps and more runs than is typical for the ALE. Experiments like this improve reproducibility, and allow us to draw more confident conclusions. We hope that MinAtar can allow researchers to thoroughly investigate behavioural challenges similar to those inherent in the ALE.
Code (3)
Tasks
Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Estimating Risk and Uncertainty in Deep Reinforcement Learning
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and mu…
Bayesian InferenceDeep Reinforcement LearningDistributional Reinforcement LearningEfficient Exploration+3Graph Backup: Data Efficient Backup Exploiting Markovian Transitions
The successes of deep Reinforcement Learning (RL) are limited to settings where we have a large stream of online experiences, but applying RL in the data-efficient setting with limited access to online interactions is st…
Atari GamescounterfactualDeep Reinforcement LearningQ-Learning+1Deep Conservative Policy Iteration
Conservative Policy Iteration (CPI) is a founding algorithm of Approximate Dynamic Programming (ADP). Its core principle is to stabilize greediness through stochastic mixtures of consecutive policies. It comes with stron…
Atari GamesDeep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning
We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\textit{Cal…
Atari GamesDistributional Reinforcement Learningquantile regressionregression+1Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-ineff…
Reinforcement Learning