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.
Parametrically Retargetable Decision-Makers Tend To Seek Power
Emergence of Novelty in Evolutionary Algorithms
Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration
DNA: Proximal Policy Optimization with a Dual Network Architecture
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
IGN : Implicit Generative Networks
Deep Hierarchical Planning from Pixels
Generalized Data Distribution Iteration
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Graph Backup: Data Efficient Backup Exploiting Markovian Transitions
Multi-Game Decision Transformers
Nuclear Norm Maximization Based Curiosity-Driven Learning
Deep Apprenticeship Learning for Playing Games
Learning to Constrain Policy Optimization with Virtual Trust Region
Understanding and Preventing Capacity Loss in Reinforcement Learning
Methodical Advice Collection and Reuse in Deep Reinforcement Learning
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
Temporal Alignment for History Representation in Reinforcement Learning
Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks
Learning Relational Rules from Rewards
NavDreams: Towards Camera-Only RL Navigation Among Humans
Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act
Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
On the Generalization of Representations in Reinforcement Learning
Open-Ended Reinforcement Learning with Neural Reward Functions
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search
ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Generative Adversarial Exploration for Reinforcement Learning
Deep Reinforcement Learning with Spiking Q-learning
Attention Option-Critic
Execute Order 66: Targeted Data Poisoning for Reinforcement Learning
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning
Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.