54 search results - page 4 / 11 » Convergence Results for Single-Step On-Policy Reinforcement-... |
NIPS
2001
13 years 8 months ago
2001
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
CORR
2007
Springer
13 years 7 months ago
2007
Springer
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
AAMAS
2007
Springer
13 years 7 months ago
2007
Springer
In this paper, we investigate the use of parallelization in reinforcement learning (RL), with the goal of learning optimal policies for single-agent RL problems more quickly by us...
ATAL
2010
Springer
13 years 8 months ago
2010
Springer
Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous ...
JMLR
2010
13 years 2 months ago
2010
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...