Many complex multi-agent systems such as robot swarms control and autonomous vehicle
coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a …

We identify and study the phenomenon of policy churn, that is, the rapid change of the
greedy policy in value-based reinforcement learning. Policy churn operates at a surprisingly …

Multistep returns, such as $ n $-step returns and $\lambda $-returns, are commonly used to
improve the sample efficiency of reinforcement learning (RL) methods. The variance of the …

We investigate the use of animal videos (observations) to improve Reinforcement Learning
(RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by …

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement
learning, but counteracting off-policy bias without exacerbating variance is challenging …

We study the multi-step off-policy learning approach to distributional RL. Despite the
apparent similarity between value-based RL and distributional RL, our study reveals …

The recency heuristic in reinforcement learning is the assumption that stimuli that occurred
closer in time to an acquired reward should be more heavily reinforced. The recency …

How to make intelligent decisions is a central problem in machine learning and artificial
intelligence. Despite recent successes of deep reinforcement learning (RL) in various …

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance
but still require better explanations. To this end, we show its policy evaluation error on the …

Multi-step learning applies lookahead over multiple time steps and has proved valuable in
policy evaluation settings. However, in the optimal control case, the impact of multi-step …