arXiv research

Agent57 beats human average on all Atari games.

Method learns state representations without supervision for Atari games.

Proposes a new Deep Recurrent Double Q-Learning model for Atari games.

DreamerV2 learns Atari game behaviors from a world model, achieving human-level performance.

Generative deep learning creates counterfactual states to explain Atari agent decisions.

A new RL method improves performance on Atari games without complex techniques.

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so…

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 requ…

TOYBOX creates new Atari environments for deep RL experiments.

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games. We identify three key challenges that any algorithm needs to master in order to perform well on all games: process…

A new RL method boosts exploration efficiency in Atari games and driving simulators.

Paper proposes a new method for better estimating continuous distributions in RL.

AG-RL uses action grammars to improve reinforcement learning efficiency.

This paper benchmarks batch RL algorithms on Atari, finding DQN and partially-trained policies perform best.

CuLE accelerates reinforcement learning on GPUs.

A new reward learning module improves imitation learning in high-dimensional environments.

The study explores when parametric models enhance reinforcement learning, validating a hypothesis on Atari games.

Improved deep Q-learning with SVRG reduces variance and stabilizes training.

Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network pro…

New Soft Actor-Critic for discrete actions.

Deep reinforcement learning has become popular over recent years, showing superiority on different visual-input tasks such as playing Atari games and robot navigation. Although objects are important image elements, few work considers enhancing deep reinforcement learning with object characteristics. In this paper, we p…

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameter…

Adapting momentum from optimization to reinforcement learning.

Paper presents a new method for Bayesian deep learning that scales to Atari games.

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space.…

Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learni…

MuZero learns models to master complex games without domain knowledge.

Aims to create a world model without baggage, achieving good performance.

Bayesian REX learns Atari games from demonstrations efficiently.

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. …

Study shows popular RL methods are inefficient due to unfair baselines.

Develops a deep metric learning approach for detecting bugs in video games.

Simple object representations improve model-free RL performance.

Paper proposes an RL algorithm to ensure policy performance guarantees.

CURL uses contrastive learning to improve reinforcement learning performance.

DPFRL uses particle filters for decision making with complex visual observations.

Combines experience replay and exploration for better agent performance.

A new neural network model improves reinforcement learning efficiency.

A new method for prioritizing sequences in reinforcement learning improves learning efficiency.

Method learns statistics of return distributions via neural networks and maximum mean discrepancy.

A new method for reinforcement learning scales errors without tuning.

Study finds reinforcement learning performance plateaus due to environmental interference.

Deep learning improves reinforcement learning in video games.

New loss function equivalence reveals PER's uniform sampling can be improved.

Video games improve vehicle routing performance.

We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs avail…

Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it. By separating the image processing from decision-making, one could better …

ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.