Related papers: Mega-Reward: Achieving Human-Level Play without Ex…

An autonomous agent embodied in a humanoid robot, in order to learn from the overwhelming flow of raw and noisy sensory, has to effectively reduce the high spatial-temporal data dimensionality. In this paper we propose a novel method of…

Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajectories with deep…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Artificial Intelligence systems are rapidly evolving, integrating extrinsic and intrinsic motivations. While these frameworks offer benefits, they risk misalignment at the algorithmic level while appearing superficially aligned with human…

The success of modern civilization is built upon widespread cooperation in human society, deciphering the mechanisms behind has being a major goal for centuries. A crucial fact is, however, largely missing in most prior studies that games…

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning…

Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling…

Consider a prosthetic arm, learning to adapt to its user's control signals. We propose Interaction-Grounded Learning for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward…

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…

Autonomous navigation in crowded environments is an open problem with many applications, essential for the coexistence of robots and humans in the smart cities of the future. In recent years, deep reinforcement learning approaches have…

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

There is a broad recognition that commitment-based mechanisms can promote coordination and cooperative behaviours in both biological populations and self-organised multi-agent systems by making individuals' intentions explicit prior to…

Dealing with environments with sparse rewards has always been crucial for systems developed to operate in autonomous open-ended learning settings. Intrinsic Motivations could be an effective way to help Deep Reinforcement Learning…

Reward models (RMs), which are central to existing post-training methods, aim to align LLM outputs with human values by providing feedback signals during fine-tuning. However, existing RMs struggle to capture nuanced, user-specific…

Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human guidance, the evolution stops. In this work, we train agents to…

In this study, we address the problem of efficient exploration in reinforcement learning. Most common exploration approaches depend on random action selection, however these approaches do not work well in environments with sparse or no…

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to…

Under sparse extrinsic reward settings, reinforcement learning has remained challenging, despite surging interests in this field. Previous attempts suggest that intrinsic reward can alleviate the issue caused by sparsity. In this article,…