Related papers: Representation Alignment from Human Feedback for C…
Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…
Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of shaping methods that enable agents to learn efficiently in…
Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike…
Imitation learning from human demonstrations offers a promising approach for robot skill acquisition, but egocentric human data introduces fundamental challenges due to the embodiment gap. During manipulation, humans actively coordinate…
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…
Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…
A common view on the brain learning processes proposes that the three classic learning paradigms -- unsupervised, reinforcement, and supervised -- take place in respectively the cortex, the basal-ganglia, and the cerebellum. However,…
Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (SSL) backbones encode rich inter-class semantics of general objects, we show they fail to…
Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…
Imitation learning practitioners have often noted that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ. Interactive approaches can provably address…
Learning manipulation skills from human demonstration videos presents a promising yet challenging problem, primarily due to the significant embodiment gap between human body and robot manipulators. Existing methods rely on paired datasets…
Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…
Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection…
Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…
Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors,…
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons,…
Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…
Understanding action correspondence between humans and robots is essential for evaluating alignment in decision-making, particularly in human-robot collaboration and imitation learning within unstructured environments. We propose a…
Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous driving. Existing algorithms have focused on learning reward…
Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground…