Related papers: CRED: Counterfactual Reasoning and Environment Des…
Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…
We observe that the human trajectory is not only forward predictable, but also backward predictable. Both forward and backward trajectories follow the same social norms and obey the same physical constraints with the only difference in…
In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states.…
Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by…
Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis. From a behavioral…
Human demonstrations can provide trustful samples to train reinforcement learning algorithms for robots to learn complex behaviors in real-world environments. However, obtaining sufficient demonstrations may be impractical because many…
Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability. Through independent improvements of components such as replay buffers or more…
Reinforcement-learning agents seek to maximize a reward signal through environmental interactions. As humans, our job in the learning process is to design reward functions to express desired behavior and enable the agent to learn such…
Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation…
Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…
Robot navigation using deep reinforcement learning (DRL) has shown great potential in improving the performance of mobile robots. Nevertheless, most existing DRL-based navigation methods primarily focus on training a policy that directly…
We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. The goal of the…
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reasoning on math and code but depends on a programmatic verifier…
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where…
Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…
For a real-world decision-making problem, the reward function often needs to be engineered or learned. A popular approach is to utilize human feedback to learn a reward function for training. The most straightforward way to do so is to ask…
Autonomous mobility tasks such as lastmile delivery require reasoning about operator indicated preferences over terrains on which the robot should navigate to ensure both robot safety and mission success. However, coping with out of…
Deep reinforcement learning (RL) models, despite their efficiency in learning an optimal policy in static environments, easily loses previously learned knowledge (i.e., catastrophic forgetting). It leads RL models to poor performance in…
Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…