rl.py 430 octets
Newer Older
"""Reinforcement Learning (Chapter 21)
"""

from utils import *
import agents

MircoT's avatar
MircoT a validé

class PassiveADPAgent(agents.Agent):
MircoT's avatar
MircoT a validé

    """Passive (non-learning) agent that uses adaptive dynamic programming
    on a given MDP and policy. [Fig. 21.2]"""
MircoT's avatar
MircoT a validé

class PassiveTDAgent(agents.Agent):
MircoT's avatar
MircoT a validé

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