Related papers: From Imitation to Optimization: A Comparative Stud…
Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one…
Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In such near-accident scenarios, even a minor change in the…
Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…
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…
Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a…
Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…
Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…
Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.…
A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. However, existing works heavily rely on the purity of the data,…
This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes…
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).…
When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although…
Self-imitation learning is a Reinforcement Learning (RL) method that encourages actions whose returns were higher than expected, which helps in hard exploration and sparse reward problems. It was shown to improve the performance of…
We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…
Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this…
Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…
Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…
Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of…
Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…
A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data, using some data collection policy, and then learn from this data to perform various tasks, using offline…