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.
Learning State Representations from Random Deep Action-conditional Predictions
An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios
Revisiting Prioritized Experience Replay: A Value Perspective
Shielding Atari Games with Bounded Prescience
Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents
Hierarchical Width-Based Planning and Learning
Developing an OpenAI Gym-compatible framework and simulation environment for testing Deep Reinforcement Learning agents solving the Ambulance Location Problem
Evolving Reinforcement Learning Algorithms
Reinforcement Learning with Latent Flow
Deep Reinforcement Learning with Quantum-inspired Experience Replay
Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup
Augmenting Policy Learning with Routines Discovered from a Single Demonstration
Self-Imitation Advantage Learning
Evaluating Agents without Rewards
High-Throughput Synchronous Deep RL
Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
Selective Eye-gaze Augmentation To Enhance Imitation Learning In Atari Games
Optimizing the Neural Architecture of Reinforcement Learning Agents
Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning
Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research
Leveraging the Variance of Return Sequences for Exploration Policy
Perturbation-based exploration methods in deep reinforcement learning
Machine versus Human Attention in Deep Reinforcement Learning Tasks
Learning to Represent Action Values as a Hypergraph on the Action Vertices
VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Masked Contrastive Representation Learning for Reinforcement Learning
Smaller World Models for Reinforcement Learning
Mastering Atari with Discrete World Models
Student-Initiated Action Advising via Advice Novelty
Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks
Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy
Multiplayer Support for the Arcade Learning Environment
Reconstructing Actions To Explain Deep Reinforcement Learning
Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search
Ranking Policy Decisions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.