Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency.

Hanabi is a cooperative card game in which two to five players attempt to stack twenty-five cards into five different fireworks (piles), one for each suit (color) and by ascending rank (number).

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings .

Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years.

Stabilizing an unknown dynamical system is one of the central problems in control theory. In this paper, we study the sample complexity of the learn-to-stabilize problem in Linear Time-Invariant (L TI) systems on a single trajectory. Current state-of-the-art approaches require a sample complexity linear in n, the state dimension, which incurs a state norm that blows up exponentially in n. We propose a novel algorithm based on spectral decomposition that only needs to learn "a small part" of the dynamical matrix acting on its unstable subspace. We show that, under proper assumptions, our algorithm stabilizes an L TI system on a single trajectory with O ( k log n) samples, where k is the instability index of the system. This represents the first sub-linear sample complexity result for the stabilization of L TI systems under the regime when k = o (n).

Policy Learning (ConPoLe) that explicitly optimizes the InfoNCE loss, which lower bounds the mutual information between the current state and next states that continue on a path to the solution.

A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which require external assistance to recover from, such as when a robot arm has pushed an object off of a table.