Related papers: ARCHER: Aggressive Rewards to Counter bias in Hind…
In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might…
Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…
Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…
Actor learning and critic learning are two components of the outstanding and mostly used Deep Deterministic Policy Gradient (DDPG) reinforcement learning method. Since actor and critic learning plays a significant role in the overall…
Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped…
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive…
Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories with achieved…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…
The utilization of the experience replay mechanism enables agents to effectively leverage their experiences on several occasions. In previous studies, the sampling probability of the transitions was modified based on their relative…
Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…
Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward…
Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…
Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…
Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of…
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…
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…
Credit assignment is a fundamental problem in reinforcement learning, the problem of measuring an action's influence on future rewards. Explicit credit assignment methods have the potential to boost the performance of RL algorithms on many…
Experience replay is an essential component in deep reinforcement learning (DRL), which stores the experiences and generates experiences for the agent to learn in real time. Recently, prioritized experience replay (PER) has been proven to…
We present a novel technique called Dynamic Experience Replay (DER) that allows Reinforcement Learning (RL) algorithms to use experience replay samples not only from human demonstrations but also successful transitions generated by RL…
Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the…