Related papers: Learning Diverse Policies with Soft Self-Generated…
Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…
Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…
Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the…
In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several…
The success of popular algorithms for deep reinforcement learning, such as policy-gradients and Q-learning, relies heavily on the availability of an informative reward signal at each timestep of the sequential decision-making process. When…
Multi-goal reinforcement learning (RL) aims to qualify the agent to accomplish multi-goal tasks, which is of great importance in learning scalable robotic manipulation skills. However, reward engineering always requires strenuous efforts in…
In the Reinforcement Learning (RL) framework, the learning is guided through a reward signal. This means that in situations of sparse rewards the agent has to focus on exploration, in order to discover which action, or set of actions leads…
As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the…
Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…
Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated…
This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…
Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…
Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…
Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent to maximize expected win-rates against its current or…
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…
In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not…