rl.py 426 octets
Newer Older
"""Reinforcement Learning (Chapter 21)
"""

from utils import *
import agents

class PassiveADPAgent(agents.Agent):
    """Passive (non-learning) agent that uses adaptive dynamic programming
    on a given MDP and policy. [Fig. 21.2]"""

class PassiveTDAgent(agents.Agent):
    """Passive (non-learning) agent that uses temporal differences to learn
    utility estimates. [Fig. 21.4]"""