Multitask Reinforcement Learning is a promising way to obtain models wit...
Non-stationarity arises in Reinforcement Learning (RL) even in stationar...
Using privileged information during training can improve the sample
effi...
In a multi-agent system, an agent's optimal policy will typically depend...
We revisit residual algorithms in both model-free and model-based
reinfo...
We propose a new objective, the counterfactual objective, unifying exist...
In multi-agent reinforcement learning, centralised policies can only be
...