相关论文: Expected Eligibility Traces

The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL…

Temporal credit assignment is crucial for learning and skill development in natural and artificial intelligence. While computational methods like the TD approach in reinforcement learning have been proposed, it's unclear if they accurately…

Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards. In particular, this requires separating skill from luck, i.e. disentangling the effect of an action on rewards from that of…

Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying…

Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…

We consider the problem of data race prediction where the program's behavior is represented by a trace. A trace is a sequence of program events recorded during the execution of the program. We employ the schedulable happens-before relation…

Knowledge tracing aims to model students' past answer sequences to track the change in their knowledge acquisition during exercise activities and to predict their future learning performance. Most existing approaches ignore the fact that…

In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain…

How do we formalize the challenge of credit assignment in reinforcement learning? Common intuition would draw attention to reward sparsity as a key contributor to difficult credit assignment and traditional heuristics would look to temporal…

Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel". We dwell on our actions in the past and experience satisfaction or regret. More than merely autobiographical storytelling, we use these event…

A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provides for Time Hopping similar abilities to what eligibility…

We address the problem of credit assignment in reinforcement learning and explore fundamental questions regarding the way in which an agent can best use additional computation to propagate new information, by planning with internal models…

Since the earliest days of reinforcement learning, the workhorse method for assigning credit to actions over time has been temporal-difference (TD) learning, which propagates credit backward timestep-by-timestep. This approach suffers when…

Early Classification of Time Series (ECTS) has been recognized as an important problem in many areas where decisions have to be taken as soon as possible, before the full data availability, while time pressure increases. Numerous ECTS…

Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully…

Policy evaluation with linear function approximation is an important problem in reinforcement learning. When facing high-dimensional feature spaces, such a problem becomes extremely hard considering the computation efficiency and quality of…

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Modern software projects include automated tests written to check the programs' functionality. The set of functions invoked by a test is called the trace of the test, and the action of obtaining a trace is called tracing. There are many…

In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example,…

How much credit (or blame) should an action taken in a state get for a future reward? This is the fundamental temporal credit assignment problem in Reinforcement Learning (RL). One of the earliest and still most widely used heuristics is to…