Papers Atari Games
“Atari Games” 태그가 달린 논문 658편 · 필터 해제
Q-based Variational Inverse Reinforcement Learning
The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by hand is often infeasible. Inverse reinforcement …
Reinforcement LearningActive LearningAtari GamesAccelerating Q-learning through Efficient Value-Sharing across Actions
Action values are foundational to many control algorithms such as Q-learning. Therefore, efficient action-value learning is central to reinforcement learning (RL). However, learning them can be slow, requiring many updat…
Reinforcement LearningAtari GamesThe Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents
A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds. These two regimes sit at opposite ends of the latency-quality t…
Atari GamesMultivariate Distributional Reinforcement Learning Using Sliced Divergences
Distributional reinforcement learning (DRL) models the full return distribution rather than expectations, but extending it to multivariate settings remains challenging. Many common metrics do not naturally generalize bey…
Reinforcement LearningAtari GamesPlan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning
Ensuring the security of reinforcement learning (RL) models is critical, particularly when they are trained by third parties and deployed in real-world systems. Attackers can implant backdoors into these models, causing …
Reinforcement LearningAtari GamesRevisiting Adam for Streaming Reinforcement Learning
Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of simpler, more efficient and adaptive algorithms. For over a decade, ho…
Reinforcement LearningAtari GamesQuantile Geometry Regularization for Distributional Reinforcement Learning
Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimat…
Reinforcement LearningAtari GamesTSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds to domains where new …
Reinforcement LearningContinuous ControlContinual LearningAtari GamesGRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concepts, such as "left of" or "close by", serv…
Reinforcement LearningAtari GamesEstimating Central, Peripheral, and Temporal Visual Contributions to Human Decision Making in Atari Games
We study how different visual information sources contribute to human decision making in dynamic visual environments. Using Atari-HEAD, a large-scale Atari gameplay dataset with synchronized eye-tracking, we introduce a …
Decision MakingAtari GamesAuction-Based Online Policy Adaptation for Evolving Objectives
We consider multi-objective reinforcement learning problems where objectives come from an identical family -- such as the class of reachability objectives -- and may appear or disappear at runtime. Our goal is to design …
Reinforcement LearningAtari GamesSee, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay
Vision-Language Models (VLMs) excel at describing visual scenes, yet struggle to translate perception into precise, grounded actions. We investigate whether providing VLMs with both the visual frame and the symbolic repr…
Atari GamesContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulation
Reinforcement learning has achieved remarkable success in domains such as Atari games, navigation, and locomotion, where exploration can often be guided by novelty over states or dynamics. In contrast, dexterous manipula…
Reinforcement LearningAtari GamesGradient Iterated Temporal-Difference Learning
Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which cons…
Atari GamesOptimistic Policy Regularization
Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduc…
Reinforcement LearningAtari GamesUnifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planni…
Reinforcement LearningContinuous ControlAtari GamesFIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
Deep neural networks trained on nonstationary data must balance stability (i.e., retaining prior knowledge) and plasticity (i.e., adapting to new tasks). Standard reinitialization methods, which reinitialize weights towa…
Reinforcement LearningAtari GamesJoint Learning of Hierarchical Neural Options and Abstract World Model
Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a sequence of skills, formalized as hiera…
Atari GamesMixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit substantial heterogeneity in both observations and dynamics. Model-based reinforcem…
Reinforcement LearningAtari GamesMarti-5: A Mathematical Model of "Self in the World" as a First Step Toward Self-Awareness
The existence of 'what' and 'where' pathways of information processing in the brain was proposed almost 30 years ago, but there is still a lack of a clear mathematical model that could show how these pathways work togeth…
Reinforcement LearningAtari Games