Skip to content
Codes and description for Multi Agent RL where Markovian property is not satisfied.
Branch: master
Clone or download
agarw180
agarw180 Latest changes
Latest commit 02b1fbc Dec 5, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ipynb_checkpoints Latest changes Dec 5, 2019
__pycache__ Latest changes Dec 5, 2019
Latency_policy_gradient_complete.ipynb Latest changes Dec 5, 2019
Latency_policy_gradient_complete_test-Copy1.ipynb Latest changes Dec 5, 2019
Latency_policy_gradient_complete_test.ipynb Latest changes Dec 5, 2019
MARL_PG_basic_multi_class_SARSA.ipynb initial commit Oct 18, 2019
MARL_PG_basic_multi_class_backup-Copy1.ipynb corrected PG code file Oct 18, 2019
MARL_PG_basic_multi_class_clean.ipynb Latest changes Dec 5, 2019
MARL_value_based_convex_approximation.ipynb Latest changes Dec 5, 2019
README.md Update README.md Nov 28, 2019
Router_LQF_alpha_1_K81574439949.1235735.pickle Latest changes Dec 5, 2019
Router_SQF_alpha_1_K81574439949.1235735.pickle Latest changes Dec 5, 2019
Router_policy_gradient_alpha_1_K81574439949.1235735.pickle Latest changes Dec 5, 2019
Traffic_lane_policy_gradient_complete.ipynb Latest changes Dec 5, 2019
Untitled.ipynb Latest changes Dec 5, 2019
alpha_figure_k_8.eps Latest changes Dec 5, 2019
alpha_figure_k_8.tex Latest changes Dec 5, 2019
gauss_markov_wireless_channel.py Latest changes Dec 5, 2019
latency_alpha_figure_k_4.eps Latest changes Dec 5, 2019
latency_alpha_figure_k_4.tex Latest changes Dec 5, 2019
latency_alpha_figure_k_8.eps Latest changes Dec 5, 2019
latency_alpha_figure_k_8.tex Latest changes Dec 5, 2019
latency_envionment.ipynb Latest changes Dec 5, 2019
latency_environment.py Latest changes Dec 5, 2019
optimal_policy_fairness.jpg Latest changes Dec 5, 2019
standard_deep_policy_class.py Latest changes Dec 5, 2019
standard_policy_class.py Latest changes Dec 5, 2019
traffic_lane_environment.py Latest changes Dec 5, 2019

README.md

non-markov-RL

Codes and description for Multi Agent RL where Markovian property is not satisfied.

© M. Agarwal and V. Aggarwal.

This is the source code for paper M. Agarwal and V. Aggarwal, "Reinforcement Learning with Non-Markovian Rewards, " arXiv:1909.02940v2, Nov 2019.

Please cite the above paper if using any part of the code.

You can’t perform that action at this time.