Did I find the right examples for you? yes no      Crawl my project      Python Jobs

All Samples(67)  |  Call(17)  |  Derive(14)  |  Import(36)

src/r/l/rlpy-HEAD/rlpy/Agents/TDControlAgent.py   rlpy(Download)
"""Control Agents based on TD Learning, i.e., Q-Learning and SARSA"""
from .Agent import Agent, DescentAlgorithm
from rlpy.Tools import addNewElementForAllActions, count_nonzero
import numpy as np
 
class TDControlAgent(DescentAlgorithm, Agent):
 
    """
    abstract class for the control variants of the classical linear TD-Learning.
    It is the parent of SARSA and Q-Learning

src/r/l/rlpy-HEAD/rlpy/Agents/Greedy_GQ.py   rlpy(Download)
"""Greedy-GQ(lambda) learning agent"""
from .Agent import Agent, DescentAlgorithm
from rlpy.Tools import addNewElementForAllActions, count_nonzero
import numpy as np
from copy import copy
class Greedy_GQ(DescentAlgorithm, Agent):
    lambda_ = 0  # lambda Parameter in SARSA [Sutton Book 1998]
    eligibility_trace = []
    # eligibility trace using state only (no copy-paste), necessary for dabney
    # decay mode

src/r/l/rlpy-HEAD/rlpy/Agents/NaturalActorCritic.py   rlpy(Download)
"""
Experimental Implementation of Natural Actor Critic
"""
import numpy as np
from .Agent import Agent
class NaturalActorCritic(Agent):
 
    """
    the step-based Natural Actor Critic algorithm
    as described in algorithm 1 of

src/r/l/rlpy-HEAD/rlpy/Agents/LSPI.py   rlpy(Download)
"""Least-Squares Policy Iteration [Lagoudakis and Parr 2003]."""
from .Agent import Agent
import rlpy.Tools as Tools
import numpy as np
from scipy import sparse as sp
class LSPI(Agent):
 
    """Least Squares Policy Iteration reinforcement learning agent.
 
    Args:

src/a/i/AIQ-HEAD/agents/Random.py   AIQ(Download)
 
from random  import randint
from Agent   import Agent
 
class Random(Agent):

src/a/i/AIQ-HEAD/agents/Q_l.py   AIQ(Download)
#
 
from Agent import Agent
from numpy import zeros, ones
import numpy as np
from random import randint, randrange, random
import sys
 
 
class Q_l(Agent):

src/a/i/AIQ-HEAD/agents/Manual.py   AIQ(Download)
 
from random  import randint
from Agent   import Agent
 
import random
class Manual(Agent):
 
    def __init__( self, refm, disc_rate ):
        Agent.__init__( self, refm, disc_rate )
 

src/a/i/AIQ-HEAD/agents/HLQ_l.py   AIQ(Download)
#
 
from Agent import Agent
 
from random import randint, randrange, random
class HLQ_l(Agent):
 
    def __init__( self, refm, disc_rate, sel_mode, init_Q, Lambda, epsilon=0, gamma=0 ):
 
        Agent.__init__( self, refm, disc_rate )

src/a/i/AIQ-HEAD/agents/Freq.py   AIQ(Download)
#
 
from Agent import Agent
 
from numpy import zeros
class Freq(Agent):
 
    def __init__( self, refm, disc_rate, epsilon ):
 
        Agent.__init__( self, refm, disc_rate )

src/a/i/AIQ-HEAD/agents/MC_AIXI.py   AIQ(Download)
#
 
from Agent import Agent
from numpy import zeros, ones, ceil
import  numpy as np
class MC_AIXI(Agent):
 
    def __init__( self, refm, disc_rate, sims, depth, horizon, \
                  epsilon=0.05, threads=1, memory=32 ):
 

  1 | 2  Next