bestvibes / multi-agent-cooperation / 116

Builds Branch Commit Type Ran Committer Via Coverage
116 ryan Add a2c Able to run but results incorrect push RyanJianzhiLiu travis-ci pending completion
112 vaibhav .gitignore: ignore trained models Pull #10 web-flow travis-ci pending completion
111 vaibhav .gitignore: ignore trained models push bestvibes travis-ci pending completion
109 ryan Merge pull request #8 from bestvibes/vaibhav Policy Gradient push web-flow travis-ci pending completion
108 develop Merge pull request #8 from bestvibes/vaibhav Policy Gradient push web-flow travis-ci pending completion
107 develop Merge pull request #9 from bestvibes/ryan Continuous Environment push web-flow travis-ci pending completion
106 vaibhav Merge branch 'ryan' into vaibhav Pull #8 web-flow travis-ci pending completion
105 vaibhav Merge branch 'ryan' into vaibhav push bestvibes travis-ci pending completion
104 ryan add requirements Pull #9 web-flow travis-ci pending completion
101 ryan add requirements push bestvibes travis-ci pending completion
98 ryan Added Continuous Environment Added the implementation of a continuous environment, env_continuous.py and its tests, test_env_continuous.py push RyanJianzhiLiu travis-ci pending completion
97 ryan Reward and transition for continuous env Added reward and transition functions for continuous environment. Also added testcases for these two functions push RyanJianzhiLiu travis-ci pending completion
95 kevin Added sigmoid layer to the policy network push besth travis-ci pending completion
94 kevin added select action for pology gradient push besth travis-ci pending completion
93 kevin added policy net for policy gradient push besth travis-ci pending completion