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/amanda-lambda/hack-flappy-bird-drl

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/amaudruz/RL_openaigym

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/ameet-1997/Prioritized_Experience_Replay

Prioritized Experience Replay

https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN

Deep Reinforcement Learning with Double Q-learning

https://github.com/amzoyang/CS-221-Final-Project

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/andrejorsula/drl_grasping

Mastering Atari with Discrete World Models

https://github.com/andris955/diplomaterv

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning

https://github.com/andyljones/cule

Accelerating Reinforcement Learning through GPU Atari Emulation

https://github.com/angelolovatto/raylab

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks

Deep Reinforcement Learning with Double Q-learning

https://github.com/anhtu293/NeurIPS-2019-Challenge

Prioritized Experience Replay

https://github.com/anirudh9119/RIMs

Recurrent Independent Mechanisms

https://github.com/anita-hu/TF2-RL

Playing Atari with Deep Reinforcement Learning

https://github.com/ankeshanand/atari-representation-learning

Unsupervised State Representation Learning in Atari

https://github.com/apollopower/DOOM-AI

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

https://github.com/aravindsrinivas/curl_rainbow

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

https://github.com/ariseff/overcoming-catastrophic

Overcoming catastrophic forgetting in neural networks

https://github.com/arnomoonens/yarll

Trust Region Policy Optimization

https://github.com/ars-ashuha/quantile-regression-dqn-pytorch

Distributional Reinforcement Learning with Quantile Regression

https://github.com/asjad99/Reinforcement-Learning

Reward learning from human preferences and demonstrations in Atari

https://github.com/asparius/barlowrl

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

https://github.com/aspk/space_battle

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

https://github.com/astooke/accel_rl

Accelerated Methods for Deep Reinforcement Learning

https://github.com/astooke/rlpyt

Accelerated Methods for Deep Reinforcement Learning

https://github.com/atavakol/action-branching-agents

Deep Reinforcement Learning with Double Q-learning

https://github.com/atgambardella/pytorch-es

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

https://github.com/austinsilveria/Banana-Collection-DQN

Deep Reinforcement Learning with Double Q-learning

https://github.com/avillemin/Minecraft-AI

Playing Atari with Deep Reinforcement Learning

https://github.com/bacdavid/RND-O

Exploration by Random Network Distillation

https://github.com/backgom2357/Recommender_system_via_deep_RL

Prioritized Experience Replay

https://github.com/balloch/rl-exploration-transfer

Exploration by Random Network Distillation

https://github.com/bay3s/dqn

Playing Atari with Deep Reinforcement Learning

https://github.com/bclyang/updated-atari-env

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

https://github.com/behzaad/Deep_QLearning

Playing Atari with Deep Reinforcement Learning

https://github.com/behzadanksu/rl-attack

Noisy Networks for Exploration

https://github.com/behzadanksu/rlattack-dev

Noisy Networks for Exploration

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