
Learning Probabilistic Reward Machines from NonMarkovian Stochastic Reward Processes
The success of reinforcement learning in typical settings is, in part, p...
read it

Prophet Inequality with Competing Agents
We introduce a model of competing agents in a prophet setting, where rew...
read it

Multiagent Timebased Decisionmaking for the Search and Action Problem
Many robotic applications, such as searchandrescue, require multiple a...
read it

Episodic Curiosity through Reachability
Rewards are sparse in the real world and most today's reinforcement lear...
read it

Bayesian Persuasion in Sequential DecisionMaking
We study a dynamic model of Bayesian persuasion in sequential decisionm...
read it

'Indifference' methods for managing agent rewards
Indifference is a class of methods that are used to control a reward bas...
read it

Compounding of Wealth in ProofofStake Cryptocurrencies
Proofofstake (PoS) is a promising approach for designing efficient blo...
read it
Reinforcement with Fading Memories
We study the effect of imperfect memory on decision making in the context of a stochastic sequential actionreward problem. An agent chooses a sequence of actions which generate discrete rewards at different rates. She is allowed to make new choices at rate β, while past rewards disappear from her memory at rate μ. We focus on a family of decision rules where the agent makes a new choice by randomly selecting an action with a probability approximately proportional to the amount of past rewards associated with each action in her memory. We provide closedform formulae for the agent's steadystate choice distribution in the regime where the memory span is large (μ→ 0), and show that the agent's success critically depends on how quickly she updates her choices relative to the speed of memory decay. If β≫μ, the agent almost always chooses the best action, i.e., the one with the highest reward rate. Conversely, if β≪μ, the agent chooses an action with a probability roughly proportional to its reward rate.
READ FULL TEXT
Comments
There are no comments yet.