Reinforcement Learning
PaCo: Parameter-CompositionalMulti-Task ReinforcementLearning
Ontheotherhand,asintelligentagents,humansusuallyspendlesstime learning similar tasks and can acquire new skills using existing ones.
LearningtoPlay No-PressDiplomacy withBestResponsePolicyIteration
Weconsider Diplomacy,a7-player board game designed toaccentuate dilemmas resulting from many-agent interactions.
OnReward-FreeReinforcementLearningwith LinearFunctionApproximation
During the exploration phase, an agent collects samples without using a pre-specified reward function. After the exploration phase, a reward function is given, and the agent uses samples collected during the exploration phase to computeanear-optimalpolicy.
Provably Efficient Multi-Task Reinforcement Learning with Model Transfer
We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs).
