Related papers: Provably Efficient Exploration in Policy Optimizat…
Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…
Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to elicit chain-of-thought (CoT); however, the…
The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress…
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…
Proximal policy optimization(PPO) has been proposed as a first-order optimization method for reinforcement learning. We should notice that an exterior penalty method is used in it. Often, the minimizers of the exterior penalty functions…
Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the…
Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…
While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…
We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…
Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly…
The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…
Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function…
Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…
On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…
We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…
The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human…
We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation (OCP), an algorithm designed to synthesize efficient exploration and value…
Uncertainty estimation for Reinforcement Learning (RL) is a critical component in control tasks where agents must balance safe exploration and efficient learning. While deep neural networks have enabled breakthroughs in RL, they often lack…