Data-efficient off-policy policy evaluation for reinforcement learning
P Thomas, E Brunskill - International Conference on …, 2016 - proceedings.mlr.press
In this paper we present a new way of predicting the performance of a reinforcement
learning policy given historical data that may have been generated by a different policy. The …
learning policy given historical data that may have been generated by a different policy. The …
Meta-gradient reinforcement learning
The goal of reinforcement learning algorithms is to estimate and/or optimise the value
function. However, unlike supervised learning, no teacher or oracle is available to provide …
function. However, unlike supervised learning, no teacher or oracle is available to provide …
On monte carlo tree search and reinforcement learning
T Vodopivec, S Samothrakis, B Ster - Journal of Artificial Intelligence …, 2017 - jair.org
Fuelled by successes in Computer Go, Monte Carlo tree search (MCTS) has achieved wide-
spread adoption within the games community. Its links to traditional reinforcement learning …
spread adoption within the games community. Its links to traditional reinforcement learning …
Fast efficient hyperparameter tuning for policy gradient methods
The performance of policy gradient methods is sensitive to hyperparameter settings that
must be tuned for any new application. Widely used grid search methods for tuning …
must be tuned for any new application. Widely used grid search methods for tuning …
Automated reinforcement learning (autorl): A survey and open problems
Abstract The combination of Reinforcement Learning (RL) with deep learning has led to a
series of impressive feats, with many believing (deep) RL provides a path towards generally …
series of impressive feats, with many believing (deep) RL provides a path towards generally …
{\epsilon}-bmc: A bayesian ensemble approach to epsilon-greedy exploration in model-free reinforcement learning
Resolving the exploration-exploitation trade-off remains a fundamental problem in the
design and implementation of reinforcement learning (RL) algorithms. In this paper, we …
design and implementation of reinforcement learning (RL) algorithms. In this paper, we …
A greedy approach to adapting the trace parameter for temporal difference learning
One of the main obstacles to broad application of reinforcement learning methods is the
parameter sensitivity of our core learning algorithms. In many large-scale applications …
parameter sensitivity of our core learning algorithms. In many large-scale applications …
Fast efficient hyperparameter tuning for policy gradients
The performance of policy gradient methods is sensitive to hyperparameter settings that
must be tuned for any new application. Widely used grid search methods for tuning …
must be tuned for any new application. Widely used grid search methods for tuning …
Reinforcement learning with multiple experts: A bayesian model combination approach
Potential based reward shaping is a powerful technique for accelerating convergence of
reinforcement learning algorithms. Typically, such information includes an estimate of the …
reinforcement learning algorithms. Typically, such information includes an estimate of the …
On the Rate of Convergence and Error Bounds for LSTD (λ)
M Tagorti, B Scherrer - International Conference on Machine …, 2015 - proceedings.mlr.press
We consider LSTD (λ), the least-squares temporal-difference algorithm with eligibility traces
algorithm proposed by Boyan (2002). It computes a linear approximation of the value …
algorithm proposed by Boyan (2002). It computes a linear approximation of the value …