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/giuse/DNE

공식 코드

Playing Atari with Six Neurons

https://github.com/gomiss/action-balance-exploration

공식 코드

Exploring Unknown States with Action Balance

https://github.com/google-deepmind/sketch_dqn

공식 코드

Distributional Bellman Operators over Mean Embeddings

https://github.com/google-research/batch_rl

공식 코드

An Optimistic Perspective on Offline Reinforcement Learning

https://github.com/google-research/google-research

공식 코드

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

https://github.com/google-research/google-research/tree/master/generalization_representations_rl_aistats22

공식 코드

On the Generalization of Representations in Reinforcement Learning

https://github.com/google-research/google-research/tree/master/memento

공식 코드

On Catastrophic Interference in Atari 2600 Games

https://github.com/google-research/google-research/tree/master/mico

공식 코드

MICo: Improved representations via sampling-based state similarity for Markov decision processes

https://github.com/google-research/google-research/tree/master/multi_game_dt

공식 코드

Multi-Game Decision Transformers

https://github.com/google-research/google-research/tree/master/munchausen_rl

공식 코드

Munchausen Reinforcement Learning

https://github.com/google-research/reincarnating_rl

공식 코드

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

https://github.com/google/brain_autorl

공식 코드

Evolving Reinforcement Learning Algorithms

https://github.com/google/brain_autorl/tree/main/evolving_rl

공식 코드

Evolving Reinforcement Learning Algorithms

https://github.com/grockious/deepsynth

공식 코드

DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning

https://github.com/gsastry/human-rl

공식 코드

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention

https://github.com/guillermopuebla/rrl

공식 코드

Learning Relational Rules from Rewards

https://github.com/hadrien-pouget/Ranking-Policy-Decisions

공식 코드

Ranking Policy Decisions

https://github.com/harfang3d/dogfight-sandbox-hg2

공식 코드

Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts

https://github.com/hellochick/FICM

공식 코드

Exploration via Flow-Based Intrinsic Rewards

https://github.com/htdt/tempal

공식 코드

Temporal Alignment for History Representation in Reinforcement Learning

https://github.com/ibm/atari-active-learning

공식 코드

Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari

https://github.com/improbable-ai/eipo

공식 코드

Redeeming Intrinsic Rewards via Constrained Optimization

https://github.com/inspirai/wilderness-scavenger

공식 코드

WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments

https://github.com/intelligent-control-lab/absolute-policy-optimization

공식 코드

Absolute Policy Optimization

https://github.com/iskandor/snd

공식 코드

Self-supervised network distillation: an effective approach to exploration in sparse reward environments

https://github.com/jeanharb/a2oc_delib

공식 코드

When Waiting is not an Option : Learning Options with a Deliberation Cost

https://github.com/jessefarebro/dqn-ale

공식 코드

Generalization and Regularization in DQN

https://github.com/junhyukoh/self-imitation-learning

공식 코드

Self-Imitation Learning

https://github.com/junhyukoh/value-prediction-network

공식 코드

Value Prediction Network

https://github.com/justkim/two-player-atari-rl

공식 코드

Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games

https://github.com/jzitovsky/sbv

공식 코드

Revisiting Bellman Errors for Offline Model Selection

https://github.com/k4ntz/activation-functions

공식 코드

Adaptive Rational Activations to Boost Deep Reinforcement Learning

https://github.com/k4ntz/moc

공식 코드

Boosting Object Representation Learning via Motion and Object Continuity

https://github.com/k4ntz/oc_atari

공식 코드

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

https://github.com/kazizzad/BDQN-MxNet-Gluon

공식 코드

Efficient Exploration through Bayesian Deep Q-Networks

https://github.com/kclary/variability-RL

공식 코드

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

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