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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Loss of Plasticity in Continual Deep Reinforcement Learning
Double A3C: Deep Reinforcement Learning on OpenAI Gym Games
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
Understanding plasticity in neural networks
Self-supervised network distillation: an effective approach to exploration in sparse reward environments
Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding
Revisiting Bellman Errors for Offline Model Selection
Sample Efficient Deep Reinforcement Learning via Local Planning
Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning
Learning to Perceive in Deep Model-Free Reinforcement Learning
Simultaneously Updating All Persistence Values in Reinforcement Learning
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
Boosting Object Representation Learning via Motion and Object Continuity
Redeeming Intrinsic Rewards via Constrained Optimization
Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization
Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts
Atari-5: Distilling the Arcade Learning Environment down to Five Games
Bayesian Q-learning With Imperfect Expert Demonstrations
Paused Agent Replay Refresh
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning
Revisiting Discrete Soft Actor-Critic
Deep Q-Network for AI Soccer
Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning
MAN: Multi-Action Networks Learning
Cell-Free Latent Go-Explore
Multi-modal Siamese Network for Entity Alignment
A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games
Deep Reinforcement Learning with Swin Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.