Undirected Networks
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
The interaction is usually modeled as Markov Decision Processes (MDPs). Research on MDPs can be broadly divided into two lines based on the reward generation mechanism. The first line of work [Jaksch et al., 2010, Azar et al., 2013, 2017, He et al., 2021] considers the
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
We adopt a multi-armed bandit framework for this process, enhancing prompt selection based on the returns from online trajectories.
Predictive Attractor Models
The task of sequential memory is considered challenging for models operating under biological constraints (i.e., local synaptic computations) for many reasons, including catastrophic forgetting,
Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
While humans accomplish 72.4% of the tasks, the best
Predicting Future Actions of Reinforcement Learning Agents
Furthermore, using internal plans proves more robust to model quality compared to simulation-based approaches when predicting actions, while the results for event prediction are more mixed.
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate Fan-Ming Luo 1,2 Zuolin Tu
Recent progress has demonstrated that recurrent reinforcement learning (RL), which consists of a context encoder based on recurrent neural networks (RNNs) for unobservable state prediction and a multilayer perceptron (MLP) policy for decision making, can mitigate partial observability and serve as a robust baseline for POMDP tasks.
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Figure 1: Complex decision problems that require a good understanding of the environment's
Gated Inference Network: Inference and Learning State-Space Models
This paper advances temporal reasoning within dynamically changing high-dimensional noisy observations, focusing on a latent space that characterizes the nonlinear dynamics of objects in their environment.