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.
Accelerated Target Updates for Q-learning
Compression and Localization in Reinforcement Learning for ATARI Games
Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
Deep Policies for Width-Based Planning in Pixel Domains
Reinforcement Learning with Attention that Works: A Self-Supervised Approach
Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games
DQN with model-based exploration: efficient learning on environments with sparse rewards
Towards automatic construction of multi-network models for heterogeneous multi-task learning
Deep Reinforcement Learning with Decorrelation
Reinforcement Learning with Dynamic Boltzmann Softmax Updates
Hybrid Reinforcement Learning with Expert State Sequences
Learning Self-Game-Play Agents for Combinatorial Optimization Problems
MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
Continual Learning Using World Models for Pseudo-Rehearsal
Using Natural Language for Reward Shaping in Reinforcement Learning
Model-Based Reinforcement Learning for Atari
A new Potential-Based Reward Shaping for Reinforcement Learning Agent
Metaoptimization on a Distributed System for Deep Reinforcement Learning
Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning
Visual Rationalizations in Deep Reinforcement Learning for Atari Games
Go-Explore: a New Approach for Hard-Exploration Problems
Modularization of End-to-End Learning: Case Study in Arcade Games
Combinational Q-Learning for Dou Di Zhu
Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning
Information-Directed Exploration for Deep Reinforcement Learning
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
KF-LAX: Kronecker-factored curvature estimation for control variate optimization in reinforcement learning
Learning Montezuma's Revenge from a Single Demonstration
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents
Adapting Auxiliary Losses Using Gradient Similarity
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
Learning Finite State Representations of Recurrent Policy Networks
Analysing Results from AI Benchmarks: Key Indicators and How to Obtain Them
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.