Related papers: Reinforcement Learning with Segment Feedback
Preference-based reinforcement learning (PbRL) promises to learn a complex reward function with binary human preference. However, such human-in-the-loop formulation requires considerable human effort to assign preference labels to segment…
While reinforcement learning (RL) has been successful in natural language processing (NLP) domains such as dialogue generation and text-based games, it typically faces the problem of sparse rewards that leads to slow or no convergence.…
We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…
Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric…
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still…
This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates…
The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…
Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…
The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…
We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few…
A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when…
Major depressive disorder (MDD) presents challenges in diagnosis and treatment due to its complex and heterogeneous nature. Emerging evidence indicates that reward processing abnormalities may serve as a behavioral marker for MDD. To…
Reinforcement learning (RL) algorithms assume that users specify tasks by manually writing down a reward function. However, this process can be laborious and demands considerable technical expertise. Can we devise RL algorithms that instead…
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial…
Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available,…
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…
Reinforcement learning from human feedback (RLHF) has become a key factor in aligning model behavior with users' goals. However, while humans integrate multiple strategies when making decisions, current RLHF approaches often simplify this…
Measuring states in reinforcement learning (RL) can be costly in real-world settings and may negatively influence future outcomes. We introduce the Actively Observable Markov Decision Process (AOMDP), where an agent not only selects control…