相关论文: R-AIF: Solving Sparse-Reward Robotic Tasks from Pi…

A tenet of reinforcement learning is that the agent always observes rewards. However, this is not true in many realistic settings, e.g., a human observer may not always be available to provide rewards, sensors may be limited or…

We present a method for active inference with partial observations in stochastic systems through incentive design, also known as the leader-follower game. Consider a leader agent who aims to infer a follower agent's type given a finite set…

Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In…

Recent benchmarks for memory-augmented reinforcement learning (RL) have introduced partially observable Markov decision process (POMDP) environments in which agents must use historical observations to make decisions. However, these…

Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to…

Despite the potential of active inference for visual-based control, learning the model and the preferences (priors) while interacting with the environment is challenging. Here, we study the performance of a deep active inference (dAIF)…

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other…

Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world…

Planning under uncertainty is critical to robotics. The Partially Observable Markov Decision Process (POMDP) is a mathematical framework for such planning problems. It is powerful due to its careful quantification of the non-deterministic…

This paper presents a novel approach to improving autonomous vehicle control in environments lacking clear road markings by integrating a diffusion-based motion predictor within an Active Inference Framework (AIF). Using a simulated parking…

Partial observability and uncertainty are common problems in sequential decision-making that particularly impede the use of formal models such as Markov decision processes (MDPs). However, in practice, agents may be able to employ costly…

We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the…

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions. However, learning an…

Most reinforcement learning algorithms are based on a key assumption that Markov decision processes (MDPs) are stationary. However, non-stationary MDPs with dynamic action space are omnipresent in real-world scenarios. Yet problems of…

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process…

This paper investigates manipulation of multiple unknown objects in a crowded environment. Because of incomplete knowledge due to unknown objects and occlusions in visual observations, object observations are imperfect and action success is…

In the last decade, the free energy principle (FEP) and active inference (AIF) have achieved many successes connecting conceptual models of learning and cognition to mathematical models of perception and action. This effort is driven by a…

Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the lack…

Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random sensor delays in POMDPs, where observations may arrive…