Related papers: Intrinsic Robotic Introspection: Learning Internal…

Recent reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. However, autonomous vehicles trained in simulation often struggle to work well in the real world due to the fidelity gap…

Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learning from demonstration depends crucially on inductive bias in…

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to…

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must…

We extend the framework of efficient coding, which has been used to model the development of sensory processing in isolation, to model the development of the perception/action cycle. Our extension combines sparse coding and reinforcement…

Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing. Such image captioning methods are…

To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of…

Using a model of the environment, reinforcement learning agents can plan their future moves and achieve superhuman performance in board games like Chess, Shogi, and Go, while remaining relatively sample-efficient. As demonstrated by the…

In this paper, we study the problem of reinforcement learning in multi-agent systems where communication among agents is limited. We develop a decentralized actor-critic learning framework in which each agent performs several local updates…

Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt…

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic…

In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes…

Deep reinforcement learning (DRL) provides a promising way for intelligent agents (e.g., autonomous vehicles) to learn to navigate complex scenarios. However, DRL with neural networks as function approximators is typically considered a…

Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments. These exploration algorithms have been shown to allow real world robots to…

This review proposes an integrative framework grounded on interoception and embodied AI-termed the interoceptive machine framework-that translates biologically inspired principles of internal-state regulation into computational…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Robot introspection, as opposed to anomaly detection typical in process monitoring, helps a robot understand what it is doing at all times. A robot should be able to identify its actions not only when failure or novelty occurs, but also as…

This study proposes a novel learning paradigm for spiking neural networks (SNNs) that replaces the perceptron-inspired abstraction with biologically grounded neuron models, jointly optimizing synaptic weights and intrinsic neuronal…

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is…

There have been several attempts at modeling context in robots. However, either these attempts assume a fixed number of contexts or use a rule-based approach to determine when to increment the number of contexts. In this paper, we pose the…