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.
Momentum in Reinforcement Learning
Parallel Exploration via Negatively Correlated Search
Soft Actor-Critic for Discrete Action Settings
Reinforcement Learning with Structured Hierarchical Grammar Representations of Actions
Formal Language Constraints for Markov Decision Processes
Playing Atari Ball Games with Hierarchical Reinforcement Learning
Harnessing Structures for Value-Based Planning and Reinforcement Learning
Off-Policy Actor-Critic with Shared Experience Replay
Active inference: demystified and compared
Recurrent Independent Mechanisms
Biased Estimates of Advantages over Path Ensembles
Reinforcement Learning and Video Games
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games
Reusing Convolutional Activations from Frame to Frame to Speed up Training and Inference
Performing Deep Recurrent Double Q-Learning for Atari Games
Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment
Hindsight Trust Region Policy Optimization
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning
Characterizing Attacks on Deep Reinforcement Learning
Accelerating Reinforcement Learning through GPU Atari Emulation
An Optimistic Perspective on Offline Reinforcement Learning
In Hindsight: A Smooth Reward for Steady Exploration
Deep Conservative Policy Iteration
Reward Prediction Error as an Exploration Objective in Deep RL
Unsupervised State Representation Learning in Atari
Learning Powerful Policies by Using Consistent Dynamics Model
Clustered Reinforcement Learning
Reinforcement Learning with Low-Complexity Liquid State Machines
CopyCAT: Taking Control of Neural Policies with Constant Attacks
Beyond Exponentially Discounted Sum: Automatic Learning of Return Function
Exploration via Flow-Based Intrinsic Rewards
Combining Experience Replay with Exploration by Random Network Distillation
Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.