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.
Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors
Deep Reinforcement Learning Boosted by External Knowledge
Assumed Density Filtering Q-learning
A Deeper Look at Experience Replay
Crossmodal Attentive Skill Learner
Implementing the Deep Q-Network
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
Eigenoption Discovery through the Deep Successor Representation
Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
Distributional Reinforcement Learning with Quantile Regression
Rainbow: Combining Improvements in Deep Reinforcement Learning
Exploration in Feature Space for Reinforcement Learning
Deep Abstract Q-Networks
Deep Reinforcement Learning that Matters
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
When Waiting is not an Option : Learning Options with a Deliberation Cost
Shared Learning : Enhancing Reinforcement in $Q$-Ensembles
Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning
Mean Actor Critic
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
A Distributional Perspective on Reinforcement Learning
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Value Prediction Network
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Noisy Networks for Exploration
Count-Based Exploration in Feature Space for Reinforcement Learning
Deep reinforcement learning from human preferences
Shallow Updates for Deep Reinforcement Learning
Atari games and Intel processors
Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
On Improving Deep Reinforcement Learning for POMDPs
Investigating Recurrence and Eligibility Traces in Deep Q-Networks
Beating Atari with Natural Language Guided Reinforcement Learning
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
Deep Reinforcement Learning framework for Autonomous Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.