Papers with Code 아카이브
Atari Games
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/kenjyoung/MinAtar
공식 코드MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
https://github.com/keqinw/man
공식 코드https://github.com/khurramjaved96/atari-prediction-benchmark
공식 코드Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
https://github.com/kzl/decision-transformer
공식 코드Decision Transformer: Reinforcement Learning via Sequence Modeling
https://github.com/leor-c/m3
공식 코드Uncovering Untapped Potential in Sample-Efficient World Model Agents
https://github.com/leor-c/simulus
공식 코드Uncovering Untapped Potential in Sample-Efficient World Model Agents
https://github.com/lili-chen/SEER
공식 코드Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
https://github.com/liuxhym/adapmen
공식 코드How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
https://github.com/lns/dapo
공식 코드https://github.com/luciferkonn/dt_mem
공식 코드Think Before You Act: Decision Transformers with Working Memory
https://github.com/mafi412/evolution-strategies-and-decision-transformers
공식 코드Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning
https://github.com/maitchison/PPO
공식 코드DNA: Proximal Policy Optimization with a Dual Network Architecture
https://github.com/maitchison/atari-5
공식 코드Atari-5: Distilling the Arcade Learning Environment down to Five Games
https://github.com/manueleberhardinger/ec-rl
공식 코드https://github.com/matrl-project/matrl
공식 코드A Game-Theoretic Approach to Multi-Agent Trust Region Optimization
https://github.com/mchldann/SpectralDQN
공식 코드Adapting to Reward Progressivity via Spectral Reinforcement Learning
https://github.com/mcmachado/b-pro
공식 코드State of the Art Control of Atari Games Using Shallow Reinforcement Learning
https://github.com/mcmachado/count_based_exploration_sr
공식 코드https://github.com/mcmachado/options
공식 코드A Laplacian Framework for Option Discovery in Reinforcement Learning
https://github.com/mengli11235/mst_dim
공식 코드Unsupervised Representation Learning in Partially Observable Atari Games
https://github.com/mengli11235/swin-dqn
공식 코드https://github.com/mgoulao/tov-vicreg
공식 코드https://github.com/miguelsvasco/muse
공식 코드https://github.com/mila-iqia/SGI
공식 코드Pretraining Representations for Data-Efficient Reinforcement Learning
https://github.com/mila-iqia/atari-representation-learning
공식 코드https://github.com/ml-jku/baselines-rudder
공식 코드https://github.com/ml-jku/rudder
공식 코드https://github.com/ml-research/rational_activations
공식 코드Adaptive Rational Activations to Boost Deep Reinforcement Learning
https://github.com/ml-research/rational_rl
공식 코드Adaptive Rational Activations to Boost Deep Reinforcement Learning
https://github.com/ml-research/rational_sl
공식 코드Adaptive Rational Activations to Boost Deep Reinforcement Learning
https://github.com/modanesh/Differential_IG
공식 코드Re-understanding Finite-State Representations of Recurrent Policy Networks
https://github.com/mohmdelsayed/streaming-drl
공식 코드https://github.com/mwydmuch/ViZDoom
공식 코드ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning
https://github.com/nadavbh12/Retro-Learning-Environment
공식 코드https://github.com/navneet-nmk/pytorch-rl
공식 코드Empowerment-driven Exploration using Mutual Information Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.