Related papers: Batch Policy Gradient Methods for Improving Neural…
Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate…
Driven by the rapid growth of machine learning, recent advances in game artificial intelligence (AI) have significantly impacted productivity across various gaming genres. Reward design plays a pivotal role in training game AI models,…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…
We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system…
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…
Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…
Recommendation algorithms have been pivotal in handling the overwhelming volume of online content. However, these algorithms seldom consider direct user input, resulting in superficial interaction between them. Efforts have been made to…
This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…
Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision…
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…
Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…
A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…
Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot…
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisation task, which attempts to find a policy describing how to…
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by…
The ability to learn from large batches of autonomously collected data for policy improvement -- a paradigm we refer to as batch online reinforcement learning -- holds the promise of enabling truly scalable robot learning by significantly…
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to…
Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards:…
Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…