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/crazydonkey200/neural-symbolic-machines

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

https://github.com/czen88/qtrader

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

https://github.com/czero69/acomoeye-NN

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

https://github.com/dalxndr/NEURO140

Overcoming catastrophic forgetting in neural networks

https://github.com/danielpolimac/Ispit_Inteligentni_Agenti

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/danielytan/doom_DQN

A Deeper Look at Experience Replay

https://github.com/danijar/director

Deep Hierarchical Planning from Pixels

https://github.com/dannysdeng/dqn-pytorch

Distributed Prioritized Experience Replay

https://github.com/daskol/paper-reviews

Overcoming catastrophic forgetting in neural networks

https://github.com/david-knigge/overcoming-catastrophic-forgetting-fncm-uva

Overcoming catastrophic forgetting in neural networks

https://github.com/daviddcho/supermario

Playing Atari with Deep Reinforcement Learning

https://github.com/dazcona/obstacletower

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

https://github.com/deconlabs/Binanace-trading-simulation

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/deconlabs/Binanace_trading_simulation

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/deepmind/acme/tree/master/acme/agents/jax/dqn

Munchausen Reinforcement Learning

https://github.com/deepmind/haiku

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

https://github.com/deepmind/open_spiel

Fast deep reinforcement learning using online adjustments from the past

https://github.com/deepmind/rlax

Deep Reinforcement Learning with Double Q-learning

https://github.com/deepmind/streetlearn

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

https://github.com/deniztekalp/comp-491-bitirme

Beating Atari with Natural Language Guided Reinforcement Learning

https://github.com/dickreuter/neuron_poker

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/dido1998/Recurrent-Independent-Mechanisms

Recurrent Independent Mechanisms

https://github.com/dmiracle/muzero-starter

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

https://github.com/dominusmi/FractalAI.jl

Fractal AI: A fragile theory of intelligence

https://github.com/drforester/Q-learning-Intersection-Crossing

Playing Atari with Deep Reinforcement Learning

https://github.com/dsapandora/s_cera

Rainbow: Combining Improvements in Deep Reinforcement Learning

https://github.com/dsgiitr/rl_2048

Playing Atari with Deep Reinforcement Learning

https://github.com/dsinghnegi/atari_RL_agent

Asynchronous Methods for Deep Reinforcement Learning

https://github.com/dtak/hip-mdp-public

Prioritized Experience Replay

https://github.com/dxyang/DQN_pytorch

Deep Reinforcement Learning with Double Q-learning

https://github.com/e155763/GAN-RL

Surprising Negative Results for Generative Adversarial Tree Search

https://github.com/eac-replication/eac-replication

Accelerated Methods for Deep Reinforcement Learning

https://github.com/eddynelson/dqn

Playing Atari with Deep Reinforcement Learning

https://github.com/edmundmills/basalt-competition

IQ-Learn: Inverse soft-Q Learning for Imitation

https://github.com/efg59/Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

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