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.
A Principled Path to Fitted Distributional Evaluation
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Meta-learning how to Share Credit among Macro-Actions
TextAtari: 100K Frames Game Playing with Language Agents
Improving Performance of Spike-based Deep Q-Learning using Ternary Neurons
Action-Dependent Optimality-Preserving Reward Shaping
PoE-World: Compositional World Modeling with Products of Programmatic Experts
Automatic Reward Shaping from Confounded Offline Data
Unraveling the Rainbow: can value-based methods schedule?
Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents
SwitchMT: An Adaptive Context Switching Methodology for Scalable Multi-Task Learning in Intelligent Autonomous Agents
Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning
Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning
Adventurer: Exploration with BiGAN for Deep Reinforcement Learning
APF+: Boosting adaptive-potential function reinforcement learning methods with a W-shaped network for high-dimensional games
Target Return Optimizer for Multi-Game Decision Transformer
OptionZero: Planning with Learned Options
Learning To Explore With Predictive World Model Via Self-Supervised Learning
Uncovering Untapped Potential in Sample-Efficient World Model Agents
Reinforcement Learning in Strategy-Based and Atari Games: A Review of Google DeepMinds Innovations
Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
Objects matter: object-centric world models improve reinforcement learning in visually complex environments
Divergence-Augmented Policy Optimization
Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning
Group-Agent Reinforcement Learning with Heterogeneous Agents
A quantum-classical reinforcement learning model to play Atari games
MTSpark: Enabling Multi-Task Learning with Spiking Neural Networks for Generalist Agents
From Code to Play: Benchmarking Program Search for Games Using Large Language Models
Conformal Symplectic Optimization for Stable Reinforcement Learning
Decision Transformer vs. Decision Mamba: Analysing the Complexity of Sequential Decision Making in Atari Games
Why the Agent Made that Decision: Explaining Deep Reinforcement Learning with Vision Masks
Interpreting the Learned Model in MuZero Planning
Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications
Enhancing Chess Reinforcement Learning with Graph Representation
CALE: Continuous Arcade Learning Environment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.