Related papers: Reward-Zero: Language Embedding Driven Implicit Re…

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents…

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods…

Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavior can emerge requires expert knowledge, especially for…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Building Behavioral Foundation Models (BFMs) for humanoid robots has the potential to unify diverse control tasks under a single, promptable generalist policy. However, existing approaches are either exclusively deployed on simulated…

Reinforcement learning is increasingly used for code-centric tasks. These tasks include code generation, summarization, understanding, repair, testing, and optimization. This trend is growing faster with large language models and autonomous…

Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face…

Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental…

Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To address this, we introduce L-Zero (L0), a scalable, end-to-end…

In many reinforcement learning (RL) problems, it takes some time until a taken action by the agent reaches its maximum effect on the environment and consequently the agent receives the reward corresponding to that action by a delay called…

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation.…

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation. This explanation highlights how available information in a specific query is utilised and supplemented with information a reasoner…

Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated…

Controlled text generation tasks such as unsupervised text style transfer have increasingly adopted the use of Reinforcement Learning (RL). A major challenge in applying RL to such tasks is the sparse reward, which is available only after…

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves…