Search Results for author:
Found 19 papers, 10 papers with code
On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
We empirically evaluate PROPS on both continuous-action MuJoCo benchmark tasks as well as discrete-action tasks and demonstrate that (1) PROPS decreases sampling error throughout training and (2) improves the data efficiency of on-policy policy gradient algorithms.
State-Action Similarity-Based Representations for Off-Policy Evaluation
Instead, in this paper, we seek to enhance the data-efficiency of FQE by first transforming the fixed dataset using a learned encoder, and then feeding the transformed dataset into FQE.
Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning
In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data.
Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates
Recently, data augmentation (DA) has emerged as a method for leveraging domain knowledge to inexpensively generate additional data in reinforcement learning (RL) tasks, often yielding substantial improvements in data efficiency.
Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
This latter objective is called stability and is especially important when the state space is unbounded, such that the states can be arbitrarily far from each other and the agent can drift far away from the desired states.
Safe Evaluation For Offline Learning: Are We Ready To Deploy?
In our setting, we assume a source of data, which we split into a train-set, to learn an offline policy, and a test-set, to estimate a lower-bound on the offline policy using off-policy evaluation with bootstrapping.
Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction
We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\pi_e$, using a fixed dataset, $\mathcal{D}$, collected by one or more policies that may be different from $\pi_e$.
A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret
The learning process in JIRL assumes the availability of a baseline policy and is designed with two objectives in mind \textbf{(a)} leveraging the baseline's online demonstrations to minimize the regret w. r. t the baseline policy during training, and \textbf{(b)} eventually surpassing the baseline performance.
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training.
Multi-agent Databases via Independent Learning
Thus, the paper attempts to address the question "Is it possible to design a database consisting of various learned components that cooperatively work to improve end-to-end query latency?".
ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling
This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs).
Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning
Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy.
Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration
Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters.
Towards Quantum-Secure Authentication and Key Agreement via Abstract Multi-Agent Interaction
Authentication and key agreement are decided based on the agents' observed behaviors during the interaction.
Learning an Interpretable Traffic Signal Control Policy
Given such a safety-critical domain, the affiliated actuation policy is required to be interpretable in a way that can be understood and regulated by a human.
RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration
Augmenting reinforcement learning with imitation learning is often hailed as a method by which to improve upon learning from scratch.
Importance Sampling Policy Evaluation with an Estimated Behavior Policy
We find that this estimator often lowers the mean squared error of off-policy evaluation compared to importance sampling with the true behavior policy or using a behavior policy that is estimated from a separate data set.
Data-Efficient Policy Evaluation Through Behavior Policy Search
The standard unbiased technique for evaluating a policy is to deploy the policy and observe its performance.
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation
In this context, we propose two bootstrapping off-policy evaluation methods which use learned MDP transition models in order to estimate lower confidence bounds on policy performance with limited data in both continuous and discrete state spaces.
