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/awjuliani/deep-rl-plasticity

공식 코드

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning

https://github.com/bartekcupial/finetuning-rl-as-cl

공식 코드

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem

https://github.com/belimmer/PerturbationSaliencyEvaluation

공식 코드

Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents

https://github.com/bit1029public/ADRQN

공식 코드

On Improving Deep Reinforcement Learning for POMDPs

https://github.com/bjliaa/c2d

공식 코드

Conjugated Discrete Distributions for Distributional Reinforcement Learning

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

공식 코드

Reconciling $λ$-Returns with Experience Replay

https://github.com/brett-daley/virtual-replay-cache

공식 코드

Virtual Replay Cache

https://github.com/burcukoglu/p4o-predictiveprocessingppo

공식 코드

Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

https://github.com/cjreinforce/jowa

공식 코드

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

https://github.com/coco66/ADFQ

공식 코드

Assumed Density Filtering Q-learning

https://github.com/coldsummerday/SD-SAC

공식 코드

Revisiting Discrete Soft Actor-Critic

https://github.com/conglu1997/intelligent-go-explore

공식 코드

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

https://github.com/cooper-org/cooper

공식 코드

Active Reinforcement Learning for Robust Building Control

https://github.com/cxxgtxy/POP3D

공식 코드

Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization

https://github.com/daanklijn/neurocoevolution

공식 코드

A coevolutionary approach to deep multi-agent reinforcement learning

https://github.com/danieldugas/navdreams

공식 코드

NavDreams: Towards Camera-Only RL Navigation Among Humans

https://github.com/danieleugenioneves/comper-release-results

공식 코드

Improving Experience Replay through Modeling of Similar Transitions' Sets

https://github.com/danijar/dreamerv2

공식 코드

Mastering Atari with Discrete World Models

https://github.com/datake/sinkhorndistrl

공식 코드

Distributional Reinforcement Learning with Regularized Wasserstein Loss

https://github.com/deepmind/deepmind-research/tree/master/rl_unplugged

공식 코드

RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning

https://github.com/deepmind/scalable_agent

공식 코드

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

https://github.com/deepmind/spectral_inference_networks

공식 코드

Spectral Inference Networks: Unifying Deep and Spectral Learning

https://github.com/deepsense-ai/Distributed-BA3C

공식 코드

Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes

https://github.com/demosthen/activerl

공식 코드

Active Reinforcement Learning for Robust Building Control

https://github.com/dixantmittal/expose

공식 코드

ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search

https://github.com/dojeon-ai/atari-pb

공식 코드

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

https://github.com/dsbrown1331/bayesianrex

공식 코드

Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences

https://github.com/duyunshu/lucid-dreaming-for-exp-replay

공식 코드

Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy

https://github.com/ercumentilhan/advice-imitation-reuse

공식 코드

Learning on a Budget via Teacher Imitation

https://github.com/ercumentilhan/advice-novelty

공식 코드

Student-Initiated Action Advising via Advice Novelty

https://github.com/ercumentilhan/naive-advice-imitation

공식 코드

Action Advising with Advice Imitation in Deep Reinforcement Learning

https://github.com/facebookresearch/ELF

공식 코드

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

https://github.com/facebookresearch/e3b

공식 코드

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

https://github.com/farama-foundation/arcade-learning-environment

공식 코드

CALE: Continuous Arcade Learning Environment

https://github.com/fmorenovr/DRDQ-Atari

공식 코드

Performing Deep Recurrent Double Q-Learning for Atari Games

https://github.com/gabrieledcjr/DeepRL

공식 코드

Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning

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