Related papers: Reducing Commitment to Tasks with Off-Policy Hiera…
Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and…
Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…
Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions. The eco-driving problem seeks to design optimal speed and power usage profiles based upon…
The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…
Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or…
Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is typically assumed that effective long-term planning is…
Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…
Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning. While many TD learning methods have been developed in recent years, little attention has been paid to preserving privacy and most of…
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…
Offline Reinforcement learning is commonly used for sequential decision-making in domains such as healthcare and education, where the rewards are known and the transition dynamics $T$ must be estimated on the basis of batch data. A key…
Tasks involving high-risk-high-return (HRHR) actions, such as obstacle crossing, often exhibit multimodal action distributions and stochastic returns. Most reinforcement learning (RL) methods assume unimodal Gaussian policies and rely on…
Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from poor data-efficiency and is susceptible to stochasticity in…
Unsupervised pre-training has recently become the bedrock for computer vision and natural language processing. In reinforcement learning (RL), goal-conditioned RL can potentially provide an analogous self-supervised approach for making use…
We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve sparse-reward tasks. Unlike current hierarchical RL approaches…
Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are…
We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions…
Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforcement learning can be…
Offline meta-reinforcement learning (OMRL) proficiently allows an agent to tackle novel tasks while solely relying on a static dataset. For precise and efficient task identification, existing OMRL research suggests learning separate task…