bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
JohnJim0816
2021-03-28 11:18:52 +08:00
parent 2df8d965d2
commit 6e4d966e1f
56 changed files with 497 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
codes/envs/cliff_walking.py
View File

@@ -31,7 +31,7 @@ class CliffWalkingEnv(discrete.DiscreteEnv):
self.shape = (4, 12)
nS = np.prod(self.shape)
n_actions = 4
action_dim = 4
# Cliff Location
self._cliff = np.zeros(self.shape, dtype=np.bool)
@@ -41,7 +41,7 @@ class CliffWalkingEnv(discrete.DiscreteEnv):
P = {}
for s in range(nS):
position = np.unravel_index(s, self.shape)
P[s] = { a : [] for a in range(n_actions) }
P[s] = { a : [] for a in range(action_dim) }
P[s][UP] = self._calculate_transition_prob(position, [-1, 0])
P[s][RIGHT] = self._calculate_transition_prob(position, [0, 1])
P[s][DOWN] = self._calculate_transition_prob(position, [1, 0])
@@ -51,7 +51,7 @@ class CliffWalkingEnv(discrete.DiscreteEnv):
isd = np.zeros(nS)
isd[np.ravel_multi_index((3,0), self.shape)] = 1.0
super(CliffWalkingEnv, self).__init__(nS, n_actions, P, isd)
super(CliffWalkingEnv, self).__init__(nS, action_dim, P, isd)
def render(self, mode='human', close=False):
self._render(mode, close)