Related papers: Advances in Experience Replay
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…
This paper proposes a method for prioritizing the replay experience referred to as Hindsight Goal Ranking (HGR) in overcoming the limitation of Hindsight Experience Replay (HER) that generates hindsight goals based on uniform sampling. HGR…
Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly…
Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance.…
Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…
Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error. We show that any loss function…
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such…
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite…
Reinforcement Learning (RL) algorithms typically require millions of environment interactions to learn successful policies in sparse reward settings. Hindsight Experience Replay (HER) was introduced as a technique to increase sample…
AlphaZero-like Monte Carlo Tree Search systems, originally introduced for two-player games, dynamically balance exploration and exploitation using neural network guidance. This combination makes them also suitable for classical search…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions…
This paper introduces ACS2HER, a novel integration of the Anticipatory Classifier System (ACS2) with the Hindsight Experience Replay (HER) mechanism. While ACS2 is highly effective at building cognitive maps through latent learning, its…
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…
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…
Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic…
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…
Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prioritization has to be balanced with sample diversity for…
XCS constitutes the most deeply investigated classifier system today. It bears strong potentials and comes with inherent capabilities for mastering a variety of different learning tasks. Besides outstanding successes in various…
Back-stepping experience replay (BER) is a reinforcement learning technique that can accelerate learning efficiency in reversible environments. BER trains an agent with generated back-stepping transitions of collected experiences and normal…