Open-ended learning methods that automatically generate a curriculum of
...
The availability of challenging benchmarks has played a key role in the
...
Practising and honing skills forms a fundamental component of how humans...
Progress in reinforcement learning (RL) research is often driven by the
...
In this report, we summarize the takeaways from the first NeurIPS 2021
N...
It remains a significant challenge to train generally capable agents wit...
We present an extended abstract for the previously published work TESSER...
The progress in deep reinforcement learning (RL) is heavily driven by th...
Reinforcement Learning in large action spaces is a challenging problem.
...
In many real-world settings, a team of agents must coordinate its behavi...
Centralised training with decentralised execution is an important settin...
In the last few years, deep multi-agent reinforcement learning (RL) has
...
In many real-world settings, a team of agents must coordinate their beha...