Related papers: Learning from Humans as an I-POMDP
Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or…
We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…
Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be…
Reinforcement learning algorithms are typically designed for generic Markov Decision Processes (MDPs), where any state-action pair can lead to an arbitrary transition distribution. In many practical systems, however, only a subset of the…
To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…
We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial…
Due to physiological variation, patients diagnosed with the same condition may exhibit divergent, but related, responses to the same treatments. Hidden Parameter Markov Decision Processes (HiP-MDPs) tackle this transfer-learning problem by…
Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden…
This paper is concerned with multi-view reinforcement learning (MVRL), which allows for decision making when agents share common dynamics but adhere to different observation models. We define the MVRL framework by extending partially…
Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and…
Interactive robotic grasping using natural language is one of the most fundamental tasks in human-robot interaction. However, language can be a source of ambiguity, particularly when there are ambiguous visual or linguistic contents. This…
In recent years, reinforcement learning has achieved many remarkable successes due to the growing adoption of deep learning techniques and the rapid growth in computing power. Nevertheless, it is well-known that flat reinforcement learning…
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative…
We investigate improving Monte Carlo Tree Search based solvers for Partially Observable Markov Decision Processes (POMDPs), when applied to adaptive sampling problems. We propose improvements in rollout allocation, the action exploration…
This paper deals with the question of how to most effectively conduct experiments in Partially Observed Markov Decision Processes so as to provide data that is most informative about a parameter of interest. Methods from Markov decision…
This paper proposes an integration of temporal logical reasoning and Partially Observable Markov Decision Processes (POMDPs) to achieve interpretable decision-making under uncertainty with macro-actions. Our method leverages a fragment of…
Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct…
We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts.…
The automation of factories and manufacturing processes has been accelerating over the past few years, boosted by the Industry 4.0 paradigm, including diverse scenarios with mobile, flexible agents. Efficient coordination between mobile…
This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social…