Search Results for author:
Found 23 papers, 5 papers with code
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset.
MuZero with Self-competition for Rate Control in VP9 Video Compression
Specifically, we target the problem of learning a rate control policy to select the quantization parameters (QP) in the encoding process of libvpx, an open source VP9 video compression library widely used by popular video-on-demand (VOD) services.
Competition-Level Code Generation with AlphaCode
Programming is a powerful and ubiquitous problem-solving tool.
Ranked #1 on
Code Generation
on APPS
(Introductory Pass@1000 metric)
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification
Many real-world physical control systems are required to satisfy constraints upon deployment.
Balancing Constraints and Rewards with Meta-Gradient D4PG
Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints.
An empirical investigation of the challenges of real-world reinforcement learning
We believe that an approach that addresses our set of proposed challenges would be readily deployable in a large number of real world problems.
Robust Reinforcement Learning for Continuous Control with Model Misspecification
We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms.
Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
We propose a computationally efficient algorithm that combines compressed sensing with imitation learning to solve text-based games with combinatorial action spaces.
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant.
Soft-Robust Actor-Critic Policy-Gradient
It learns an optimal policy with respect to a distribution over an uncertainty set and stays robust to model uncertainty but avoids the conservativeness of robust strategies.
Unicorn: Continual Learning with a Universal, Off-policy Agent
Some real-world domains are best characterized as a single task, but for others this perspective is limiting.
Learning Robust Options
We present a Robust Options Policy Iteration (ROPI) algorithm with convergence guarantees, which learns options that are robust to model uncertainty.
Situationally Aware Options
We learn reusable options in different scenarios in a RoboCup soccer domain (i. e., winning/losing).
Shallow Updates for Deep Reinforcement Learning
In this work we propose a hybrid approach -- the Least Squares Deep Q-Network (LS-DQN), which combines rich feature representations learned by a DRL algorithm with the stability of a linear least squares method.
Adaptive Skills Adaptive Partitions (ASAP)
We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i. e., temporally extended actions or options) as well as (2) where to apply them.
Situational Awareness by Risk-Conscious Skills
In addition, the learned risk aware skills are able to mitigate reward-based model misspecification.
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Skill distillation enables the HDRLN to efficiently retain knowledge and therefore scale in lifelong learning, by accumulating knowledge and encapsulating multiple reusable skills into a single distilled network.
Iterative Hierarchical Optimization for Misspecified Problems (IHOMP)
For complex, high-dimensional Markov Decision Processes (MDPs), it may be necessary to represent the policy with function approximation.
Adaptive Skills, Adaptive Partitions (ASAP)
We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i. e., temporally extended actions or options) as well as (2) where to apply them.
CFORB: Circular FREAK-ORB Visual Odometry
CFORB has also been run in an indoor environment and achieved an average translational error of $3. 70 \%$.
Bootstrapping Skills
The monolithic approach to policy representation in Markov Decision Processes (MDPs) looks for a single policy that can be represented as a function from states to actions.
