Papers with Code 아카이브
Atari Games
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 65
- 보존된 평가 기록
- 2,519
The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.
<span style="color:grey; opacity: 0.6">( Image credit: Playing Atari with Deep Reinforcement Learning )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Improving width-based planning with compact policies
Self-Imitation Learning
Evolving simple programs for playing Atari games
Implicit Quantile Networks for Distributional Reinforcement Learning
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces
Spectral Inference Networks: Unifying Deep and Spectral Learning
Deep Reinforcement Learning for General Video Game AI
The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces
Playing Atari with Six Neurons
Efficient Entropy for Policy Gradient with Multidimensional Action Space
Between Progress and Potential Impact of AI: the Neglected Dimensions
Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems
AGIL: Learning Attention from Human for Visuomotor Tasks
Playing hard exploration games by watching YouTube
Observe and Look Further: Achieving Consistent Performance on Atari
Monte Carlo Tree Search for Asymmetric Trees
Unsupervised Video Object Segmentation for Deep Reinforcement Learning
Episodic Memory Deep Q-Networks
Learning Time-Sensitive Strategies in Space Fortress
Progress & Compress: A scalable framework for continual learning
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning
Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control
State Distribution-aware Sampling for Deep Q-learning
On Improving Deep Reinforcement Learning for POMDPs
On Learning Intrinsic Rewards for Policy Gradient Methods
A Human Mixed Strategy Approach to Deep Reinforcement Learning
Fractal AI: A fragile theory of intelligence
Accelerated Methods for Deep Reinforcement Learning
Distributed Prioritized Experience Replay
Hierarchical Imitation and Reinforcement Learning
Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari
Learning High-level Representations from Demonstrations
Efficient Exploration through Bayesian Deep Q-Networks
Learning and Querying Fast Generative Models for Reinforcement Learning
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.