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 Game-Theoretic Approach to Multi-Agent Trust Region Optimization
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
Pretraining Representations for Data-Efficient Reinforcement Learning
Towards Practical Credit Assignment for Deep Reinforcement Learning
MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning
MICo: Improved representations via sampling-based state similarity for Markov decision processes
Decision Transformer: Reinforcement Learning via Sequence Modeling
An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning
Provable Representation Learning for Imitation with Contrastive Fourier Features
GMAC: A Distributional Perspective on Actor-Critic Framework
Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
Return-based Scaling: Yet Another Normalisation Trick for Deep RL
CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration
InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Adapting to Reward Progressivity via Spectral Reinforcement Learning
Learning on a Budget via Teacher Imitation
Action Advising with Advice Imitation in Deep Reinforcement Learning
Muesli: Combining Improvements in Policy Optimization
Online and Offline Reinforcement Learning by Planning with a Learned Model
A coevolutionary approach to deep multi-agent reinforcement learning
Bayesian Distributional Policy Gradients
Generalizable Episodic Memory for Deep Reinforcement Learning
Behavior From the Void: Unsupervised Active Pre-Training
Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
Conservative Optimistic Policy Optimization via Multiple Importance Sampling
Addressing Action Oscillations through Learning Policy Inertia
Ensemble Bootstrapping for Q-Learning
Combining Off and On-Policy Training in Model-Based Reinforcement Learning
Return-Based Contrastive Representation Learning for Reinforcement Learning
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Q-Value Weighted Regression: Reinforcement Learning with Limited Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.