Search Results for author:
Found 12 papers, 6 papers with code
Continual Robot Learning using Self-Supervised Task Inference
Our approach learns action and intention embeddings from self-organization of the observed movement and effect parts of unlabeled demonstrations and a higher-level behavior embedding from self-organization of the joint action-intention embeddings.
Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
Our approach organizes stored transitions into a concise environment-model-like network of state-nodes and transition-edges, merging similar samples to reduce the memory size and increase pair-wise distance among samples, which increases the relevancy of each sample.
Model Predictive Control with Self-supervised Representation Learning
On the other hand, a Q function is used to provide a good long-term estimate.
Chat with the Environment: Interactive Multimodal Perception Using Large Language Models
However, it remains challenging to ground LLMs in multimodal sensory input and continuous action output, while enabling a robot to interact with its environment and acquire novel information as its policies unfold.
Learning Bidirectional Action-Language Translation with Limited Supervision and Incongruent Input
Only occasionally, a learning infant would receive a matching verbal description of an action it is committing, which is similar to supervised learning.
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations
Sound is one of the most informative and abundant modalities in the real world while being robust to sense without contacts by small and cheap sensors that can be placed on mobile devices.
Behavior Self-Organization Supports Task Inference for Continual Robot Learning
Task inference is made by finding the nearest behavior embedding to a demonstrated behavior, which is used together with the environment state as input to a multi-task policy trained with reinforcement learning to optimize performance over tasks.
Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision
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.
Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination
In this paper, we present a novel dual-system motor learning approach where a meta-controller arbitrates online between model-based and model-free decisions based on an estimate of the local reliability of the learned model.
Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space
The learned models are used to generate imagined experiences, augmenting the training set of real experiences.
Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains.
Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning
In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input.
