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.
Adversary Agnostic Robust Deep Reinforcement Learning
Contrastive Variational Reinforcement Learning for Complex Observations
Robust Deep Reinforcement Learning through Adversarial Loss
Munchausen Reinforcement Learning
Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
Distributional Reinforcement Learning via Moment Matching
Slot Contrastive Networks: A Contrastive Approach for Representing Objects
Discovering Reinforcement Learning Algorithms
Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent
DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space
Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
Attention or memory? Neurointerpretable agents in space and time
Double Prioritized State Recycled Experience Replay
Convex Regularization in Monte-Carlo Tree Search
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
Intrinsic Reward Driven Imitation Learning via Generative Model
Reinforcement Learning and its Connections with Neuroscience and Psychology
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
On Effective Parallelization of Monte Carlo Tree Search
A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning
Re-understanding Finite-State Representations of Recurrent Policy Networks
The Value-Improvement Path: Towards Better Representations for Reinforcement Learning
Gradient Monitored Reinforcement Learning
A Metric Learning Approach to Anomaly Detection in Video Games
Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps
Accelerating Deep Neuroevolution on Distributed FPGAs for Reinforcement Learning Problems
First return, then explore
Learning Dialog Policies from Weak Demonstrations
Self Punishment and Reward Backfill for Deep Q-Learning
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning
Agent57: Outperforming the Atari Human Benchmark
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
Exploring Unknown States with Action Balance
Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.