Related papers: Intrinsic Motivation for Encouraging Synergistic B…
Empowerment is an information-theoretic method that can be used to intrinsically motivate learning agents. It attempts to maximize an agent's control over the environment by encouraging visiting states with a large number of reachable next…
Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans find a variety of…
This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our architecture, called SGIM-D, allows efficient learning of high-dimensional…
Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from…
What drives exploration? Understanding intrinsic motivation is a long-standing challenge in both cognitive science and artificial intelligence; numerous objectives have been proposed and used to train agents, yet there remains a gap between…
Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will…
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent.…
Learning optimal behavior policy for each agent in multi-agent systems is an essential yet difficult problem. Despite fruitful progress in multi-agent reinforcement learning, the challenge of addressing the dynamics of whether two agents…
Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions…
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a…
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design…
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…
Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…
This paper studies the coupling of internally guided learning and social interaction, and more specifically the improvement owing to demonstrations of the learning by intrinsic motivation. We present Socially Guided Intrinsic Motivation by…
Efficient collaboration in the centralized training with decentralized execution (CTDE) paradigm remains a challenge in cooperative multi-agent systems. We identify divergent action tendencies among agents as a significant obstacle to…
Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…
Enabling legged robots to perform non-prehensile loco-manipulation is crucial for enhancing their versatility. Learning behaviors such as whole-body object pushing often requires sophisticated planning strategies or extensive task-specific…
Recent research has demonstrated the potential of reinforcement learning (RL) in enabling effective multi-robot collaboration, particularly in social dilemmas where robots face a trade-off between self-interests and collective benefits.…
Real-world applications require a robot operating in the physical world with awareness of potential risks besides accomplishing the task. A large part of risky behaviors arises from interacting with objects in ignorance of affordance. To…
Many robotic tasks are composed of a lot of temporally correlated sub-tasks in a highly complex environment. It is important to discover situational intentions and proper actions by deliberating on temporal abstractions to solve problems…