Scaling laws for single-agent reinforcement learning.
Jacob HiltonJie TangJohn SchulmanPublished in: CoRR (2023)
Keyphrases
- single agent
- reinforcement learning
- multi agent
- multi agent systems
- learning agents
- state space
- dynamic environments
- window search
- multi agent coordination
- action space
- multiple agents
- decision problems
- function approximation
- learning agent
- temporal difference
- model free
- multi agent environments
- learning algorithm
- optimal policy
- markov decision processes
- stochastic games
- action selection
- path finding
- dec pomdps
- machine learning
- optimal control
- reinforcement learning algorithms
- cooperative
- special case
- genetic algorithm
- multiagent learning
- policy gradient
- markov decision problems
- reinforcement learning methods
- objective function
- partially observable markov decision processes
- search space
- evolutionary algorithm
- dynamical systems