Related papers: Batch Policy Gradient Methods for Improving Neural…
The emergence of pretrained large language models has led to the deployment of a range of social chatbots for chitchat. Although these chatbots demonstrate language ability and fluency, they are not guaranteed to be engaging and can…
Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy…
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…
We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic environment. We…
Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, online learning can adapt to non-stationary conditions. In…
In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help improve the quality of the policy. However, it may be…
Recent progress on neural approaches for language processing has triggered a resurgence of interest on building intelligent open-domain chatbots. However, even the state-of-the-art neural chatbots cannot produce satisfying responses for…
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many…
Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…
For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing,…
Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities. However, the complexity and ``black-box'' nature of neural network-based RL policies hinder their interpretability and…
Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which…
Policy gradient methods are often applied to reinforcement learning in continuous multiagent games. These methods perform local search in the joint-action space, and as we show, they are susceptable to a game-theoretic pathology known as…
The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…
Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks are separately optimized using a disjoint network architecture…
This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…
Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…
This research introduces an innovative mathematical learning approach that integrates generative AI to cultivate a structured learning rather than quick solution. Our method combines chatbot capabilities and generative AI to offer…
Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the…