GitHub - alicejia123/PGQ01: PGQ is an approach to combine Policy Gradient and Q-Learning. This repository will contain an implementation of PGQ.

#PGQ

A summary of the paper can be found here.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
figures		figures
.gitignore		.gitignore
README.md		README.md
dqn_agent.py		dqn_agent.py
dqn_agent.pyc		dqn_agent.pyc
dueling_agent.py		dueling_agent.py
dueling_agent.pyc		dueling_agent.pyc
epsilon_greedy_policy.py		epsilon_greedy_policy.py
epsilon_greedy_policy.pyc		epsilon_greedy_policy.pyc
fixed_policies.pyc		fixed_policies.pyc
pgq_agent.py		pgq_agent.py
pgq_agent.pyc		pgq_agent.pyc
replay_buffer.py		replay_buffer.py
replay_buffer.pyc		replay_buffer.pyc
sampler.py		sampler.py
sampler.pyc		sampler.pyc
test_graph_dqn.py		test_graph_dqn.py
test_graph_dueling.py		test_graph_dueling.py
test_graph_pgq.py		test_graph_pgq.py

Provide feedback