Papers with Code 아카이브

Atari Games

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/belepi93/Ape-X

Distributed Prioritized Experience Replay

https://github.com/bentrevett/pytorch-rl

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/bfmat/agenteval

Evaluating Agents without Rewards

https://github.com/bjotho/Zelda1AI

Playing Atari with Deep Reinforcement Learning

https://github.com/bkhmsi/meta-rl-harlow

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/blakeMilner/DeepQLearning

Playing Atari with Deep Reinforcement Learning

https://github.com/bllfpc/TTokDak

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

https://github.com/bonniesjli/DQN_SR

Count-Based Exploration with the Successor Representation

https://github.com/borea17/efficient_rl

Playing Atari with Deep Reinforcement Learning

https://github.com/borhanreo/Obstacle-Avoid-Car

Playing Atari with Deep Reinforcement Learning

https://github.com/botforge/simplementation

Deep Reinforcement Learning with Double Q-learning

https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/brett-daley/fast-dqn

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/bstadie/third_person_im

Benchmarking Deep Reinforcement Learning for Continuous Control

https://github.com/caganselim/COMP541-Project

Contrastive Learning of Structured World Models

https://github.com/camall3n/atari-MAC

Mean Actor Critic

https://github.com/cannylab/casual_overhypotheses

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/cathywu/rllab-multiagent

Benchmarking Deep Reinforcement Learning for Continuous Control

https://github.com/catid/never_forget

Overcoming catastrophic forgetting in neural networks

https://github.com/cbfinn/maml_rl

Benchmarking Deep Reinforcement Learning for Continuous Control

https://github.com/cdesilv1/sc2_ai_cdes

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/cesch97/NeuroEvolution

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

https://github.com/chainer/chainerrl

Trust Region Policy Optimization

https://github.com/chandar-lab/LoCA2

Mastering Atari with Discrete World Models

https://github.com/chandar-lab/RLHive

Playing Atari with Deep Reinforcement Learning

https://github.com/chengyu2/vizdoom_rl_community_canberra

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

https://github.com/cindycia/Atari-SAC-Discrete

Distributed Prioritized Experience Replay

https://github.com/clam004/intro_continual_learning

Overcoming catastrophic forgetting in neural networks

https://github.com/clarky104/carla_aebs

Dueling Network Architectures for Deep Reinforcement Learning

https://github.com/clementbernardd/Count-Based-Exploration

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman

Deep Reinforcement Learning with Double Q-learning

https://github.com/codelion/adaptive-classifier/blob/main/src/adaptive_classifier/ewc.py

Overcoming catastrophic forgetting in neural networks

https://github.com/colindbrown/columbia-deep-learning-project

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

https://github.com/coreylowman/rl_simply

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/corl-team/CORL

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/cove9988/TradingGym

Deep Reinforcement Learning with Double Q-learning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.