Related papers: Learner-aware Teaching: Inverse Reinforcement Lear…
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives…
Understanding how goal states control behavior is a question ripe for interrogation by new methods from machine learning. These methods require large and labeled datasets to train models. To annotate a large-scale image dataset with…
This paper presents an inverse reinforcement learning~(IRL) framework for Bayesian stopping time problems. By observing the actions of a Bayesian decision maker, we provide a necessary and sufficient condition to identify if these actions…
Consider the problem setting of Interaction-Grounded Learning (IGL), in which a learner's goal is to optimally interact with the environment with no explicit reward to ground its policies. The agent observes a context vector, takes an…
Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the…
The common purpose of applying reinforcement learning (RL) to asset management is the maximization of profit. The extrinsic reward function used to learn an optimal strategy typically does not take into account any other preferences or…
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main…
Many imitation learning (IL) algorithms employ inverse reinforcement learning (IRL) to infer the intrinsic reward function that an expert is implicitly optimizing for based on their demonstrated behaviors. However, in practice, IRL-based IL…
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…
We address the problem of incrementally modeling and forecasting long-term goals of a first-person camera wearer: what the user will do, where they will go, and what goal they seek. In contrast to prior work in trajectory forecasting, our…
The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act…
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…
Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory…
Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work…
Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, but standard metrics cannot capture whether changes in preference reliably change the…
Reinforcement Learning (RL) algorithms suffer from the dependency on accurately engineered reward functions to properly guide the learning agents to do the required tasks. Preference-based reinforcement learning (PbRL) addresses that by…
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…