
-
Compatible features for Monotonic Policy Improvement
Recent policy optimization approaches have achieved substantial empirica...
read it
-
Policy Optimization Through Approximated Importance Sampling
Recent policy optimization approaches (Schulman et al., 2015a, 2017) hav...
read it
-
Disentangled Skill Embeddings for Reinforcement Learning
We propose a novel framework for multi-task reinforcement learning (MTRL...
read it
-
Model-Based Stabilisation of Deep Reinforcement Learning
Though successful in high-dimensional domains, deep reinforcement learni...
read it
-
Learning High-level Representations from Demonstrations
Hierarchical learning (HL) is key to solving complex sequential decision...
read it
-
Learning with Options that Terminate Off-Policy
A temporally abstract action, or an option, is specified by a policy and...
read it
-
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Many real-world reinforcement learning problems have a hierarchical natu...
read it
-
Forecasting day-ahead electricity prices in Europe: the importance of considering market integration
Motivated by the increasing integration among electricity markets, in th...
read it
-
Analysing Congestion Problems in Multi-agent Reinforcement Learning
Congestion problems are omnipresent in today's complex networks and repr...
read it
-
An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments
This paper explores the performance of fitted neural Q iteration for rei...
read it
-
Off-Policy Reward Shaping with Ensembles
Potential-based reward shaping (PBRS) is an effective and popular techni...
read it
-
Off-Policy Shaping Ensembles in Reinforcement Learning
Recent advances of gradient temporal-difference methods allow to learn o...
read it