Related papers: Enabling Option Learning in Sparse Rewards with Hi…
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…
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 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…
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…
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…
Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent…
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…
Hierarchical agents have the potential to solve sequential decision making tasks with greater sample efficiency than their non-hierarchical counterparts because hierarchical agents can break down tasks into sets of subtasks that only…
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…
Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant…
Reinforcement learning algorithms such as hindsight experience replay (HER) and hindsight goal generation (HGG) have been able to solve challenging robotic manipulation tasks in multi-goal settings with sparse rewards. HER achieves its…
Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics. Inspired by Hierarchical Reinforcement Learning (HRL), we propose…
In multi-goal reinforcement learning with a sparse binary reward, training agents is particularly challenging, due to a lack of successful experiences. To solve this problem, hindsight experience replay (HER) generates successful…
In this work, we propose a hierarchical reinforcement learning (HRL) structure which is capable of performing autonomous vehicle planning tasks in simulated environments with multiple sub-goals. In this hierarchical structure, the network…
Optimizing the consolidation process in container-based fulfillment centers requires trading off competing objectives such as processing speed, resource usage, and space utilization while adhering to a range of real-world operational…
Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a performance gap on tasks requiring agility. We identify a root cause: in subgoal-based HRL, the…
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…
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…
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…
The problem of sparse rewards is one of the hardest challenges in contemporary reinforcement learning. Hierarchical reinforcement learning (HRL) tackles this problem by using a set of temporally-extended actions, or options, each of which…