Related papers: Maximum Entropy Behavior Exploration for Sim2Real …

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

Online model-free reinforcement learning (RL) methods with continuous actions are playing a prominent role when dealing with real-world applications such as Robotics. However, when confronted to non-stationary environments, these methods…

Mobile robots are increasingly being employed for performing complex tasks in dynamic environments. Reinforcement learning (RL) methods are recognized to be promising for specifying such tasks in a relatively simple manner. However, the…

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…

Action-constrained reinforcement learning (RL) is a widely-used approach in various real-world applications, such as scheduling in networked systems with resource constraints and control of a robot with kinematic constraints. While the…

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…

Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mismatch: reachability seeks to maximize the set of states…

We study the model-based reward-free reinforcement learning with linear function approximation for episodic Markov decision processes (MDPs). In this setting, the agent works in two phases. In the exploration phase, the agent interacts with…

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

Studying how to fine-tune offline reinforcement learning (RL) pre-trained policy is profoundly significant for enhancing the sample efficiency of RL algorithms. However, directly fine-tuning pre-trained policies often results in sub-optimal…

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…

Reducing operation and maintenance costs is a key objective for advanced reactors in general and microreactors in particular. To achieve this reduction, developing robust autonomous control algorithms is essential to ensure safe and…

Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specific, relying on extensive per-task engineering to design…

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial…

Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy…

Exploration in an unknown environment is the core functionality for mobile robots. Learning-based exploration methods, including convolutional neural networks, provide excellent strategies without human-designed logic for the feature…

Reinforcement Learning (RL) policies are designed to predict actions based on current observations to maximize cumulative future rewards. In real-world applications (i.e., non-simulated environments), sensors are essential for measuring the…

Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the application being considered, it is often…

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…

Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences. Recent algorithms such as Hindsight Experience Replay (HER)…