Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 8 of 8 for “"Off-policy Learning"”.
-
Breaking the deadly triad in reinforcement learning
<p>Reinforcement Learning (RL) is a promising framework for solving sequential decision making problems emerging from agent-environment interactions via trial and error. Off-policy learning is one of the most important techniques in RL, which enables an RL agent to learn from agent-environment …
-
OBSERVATIONAL CAUSAL INFERENCE FOR NETWORK DATA SETTINGS
… both as a tool for improving existing machine learning techniques and as an avenue to aid decision makers in applied areas, such as health and climate science. OCI relies on a key notion, identification, which links the counterfactual of interest to the observed data via a set of assumptions. …
-
Off-policy Evaluation and Learning for Interactive Systems
Recent advances in reinforcement learning (RL) provide exciting potential for making agents learn, plan and act effectively in uncertain environments. Most existing algorithms in RL rely on known environments or the existence of a good simulator, where it is cheap to explore and collect the …
-
ROUGH TERRAIN AUTONOMOUS GROUND VEHICLE SIMULATION: CARLA SIMULATION AND DEEP LEARNING BASED PREDICTIVE MODEL
With the improvement of machine learning, computer vision, motion planning, and control, UGV (autonomous ground vehicle) research has become more prevalent. Self-driving gives rise to liberate human from driving tasks and make vehicles the true extension of home instead of a transportation method …
-
Improving Data Efficiency and Availability for Alignment
… query is prohibitively difficult, but machine learning can predict what links a user is most likely to click on. Reinforcement learning from human feedback takes ML further by learning a reward model from preference comparisons to improve an LLM's responses, rather than trying to specify good …
-
TOWARDS SPECIALIZED REINFORCEMENT LEARNING FROM DIVERSE DATA
Reinforcement learning (RL) fundamentally focuses on teaching agents how to make decisions by interacting with an environment. Unlike supervised learning approaches that learn from a fixed dataset, reinforcement learning agents learn by doing, receiving feedback as rewards or penalties based on …
-
A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms
Reinforcement learning is a framework for solving sequential decision-making problems without requiring the environmental model, and is viewed as a promising approach to achieve artificial intelligence. However, there is a huge gap between the empirical successes and the theoretical understanding …
-
Reducing sampling error in batch temporal difference learning
Temporal difference (TD) learning is one of the main foundations of modern reinforcement learning. This thesis studies the use of TD(0), a canonical TD algorithm, to estimate the value function of a given evaluation policy from a batch of data. In this batch setting, we show that TD(0) may converge …