Related papers: Action-Sufficient Goal Representations
Offline reinforcement learning is used to train policies in scenarios where real-time access to the environment is expensive or impossible. As a natural consequence of these harsh conditions, an agent may lack the resources to fully observe…
Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled…
Offline goal-conditioned reinforcement learning (GCRL) is challenging in long-horizon tasks, where distant state--goal pairs provide weak supervision and value estimates become vulnerable to accumulated bootstrapping errors. Hierarchical…
Reinforcement Learning (RL) faces significant challenges in adaptive healthcare interventions, such as dementia care, where data is scarce, decisions require interpretability, and underlying patient-state dynamic are complex and causal in…
In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences for each objective. In most existing studies, specific…
Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches…
We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in…
While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial…
Multitask Representation Learning (MRL) has emerged as a prevalent technique to improve sample efficiency in Reinforcement Learning (RL). Empirical studies have found that training agents on multiple tasks simultaneously within online and…
Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel…
Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…
Reinforcement learning (RL) in the real world necessitates the development of procedures that enable agents to explore without causing harm to themselves or others. The most successful solutions to the problem of safe RL leverage offline…
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs…
Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equivalent with respect to the reward (e.g., survival). We…
Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…
Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…
Our main contribution in this work is an empirical finding that random General Value Functions (GVFs), i.e., deep action-conditional predictions -- random both in what feature of observations they predict as well as in the sequence of…
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…
Constrained Reinforcement Learning (CRL) is a subset of machine learning that introduces constraints into the traditional reinforcement learning (RL) framework. Unlike conventional RL which aims solely to maximize cumulative rewards, CRL…