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/shiwj16/SSINet

공식 코드

Self-Supervised Discovering of Interpretable Features for Reinforcement Learning

https://github.com/sjtu-marl/malib

공식 코드

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

https://github.com/sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL-

공식 코드

Augmenting Policy Learning with Routines Discovered from a Single Demonstration

https://github.com/sjtuytc/AAAI21-RoutineAugmentedPolicyLearning

공식 코드

Augmenting Policy Learning with Routines Discovered from a Single Demonstration

https://github.com/sowmya-mp/rl_a3c_pytorch

공식 코드

Visual Transfer between Atari Games using Competitive Reinforcement Learning

https://github.com/ssg-research/ad3-action-distribution-divergence-detector

공식 코드

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

https://github.com/sureli/laber

공식 코드

Large Batch Experience Replay

https://github.com/szrlee/hyperagent

공식 코드

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

https://github.com/tensorflow/tensor2tensor

공식 코드

Model-Based Reinforcement Learning for Atari

https://github.com/teslacool/m-curl

공식 코드

Masked Contrastive Representation Learning for Reinforcement Learning

https://github.com/thaihungle/sm

공식 코드

Beyond Surprise: Improving Exploration Through Surprise Novelty

https://github.com/thanhnguyentang/mmdrl

공식 코드

Distributional Reinforcement Learning via Moment Matching

https://github.com/tiencapham/ife

공식 코드

Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning

https://github.com/tkipf/c-swm

공식 코드

Contrastive Learning of Structured World Models

https://github.com/tmoer/mcts-t

공식 코드

Monte Carlo Tree Search for Asymmetric Trees

https://github.com/tobiaslv/rad

공식 코드

Conformal Symplectic Optimization for Stable Reinforcement Learning

https://github.com/topwasu/poe-world

공식 코드

PoE-World: Compositional World Modeling with Products of Programmatic Experts

https://github.com/tuomaso/radial_rl

공식 코드

Robust Deep Reinforcement Learning through Adversarial Loss

https://github.com/tuomaso/radial_rl_v2

공식 코드

Robust Deep Reinforcement Learning through Adversarial Loss

https://github.com/uber-research/atari-model-zoo

공식 코드

An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

https://github.com/uber-research/coordconv

공식 코드

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

https://github.com/uber-research/go-explore

공식 코드

First return, then explore

https://github.com/ucbtns/dai

공식 코드

Active inference: demystified and compared

https://github.com/valeoai/rainbow-iqn-apex

공식 코드

Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field

https://github.com/wangjksjtu/rl-perturbed-reward

공식 코드

Reinforcement Learning with Perturbed Rewards

https://github.com/werner-duvaud/muzero-general

공식 코드

Mastering Atari Games with Limited Data

https://github.com/wponghiran/lsm-rl

공식 코드

Reinforcement Learning with Low-Complexity Liquid State Machines

https://github.com/xingruiyu/GIRIL

공식 코드

Intrinsic Reward Driven Imitation Learning via Generative Model

https://github.com/xinjinghao/color

공식 코드

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity

https://github.com/yewr/efficientzero

공식 코드

Mastering Atari Games with Limited Data

https://github.com/yudasong/hyq

공식 코드

Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient

https://github.com/zhao-song/Softmax-DQN

공식 코드

Revisiting the Softmax Bellman Operator: New Benefits and New Perspective

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