Related papers: Competitive Experience Replay
Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…
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.…
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…
Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…
Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…
Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under…
The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act…
Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires…
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…
Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries…
Natural language instruction following is paramount to enable collaboration between artificial agents and human beings. Natural language-conditioned reinforcement learning (RL) agents have shown how natural languages' properties, such as…
Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our…
Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…
While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance…
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…
Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL),…
Reinforcement learning (RL), a common tool in decision making, learns control policies from various experiences based on the associated cumulative return/rewards without treating them differently. Humans, on the contrary, often learn to…
For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…
Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our…