Best-checkpointing

• speedup computation and simplify code

Enjoy mode

• update naming scheme to work with enjoy mode
• unify and simplify prepath methods
• info_space now uses a ckpt for loading ckpt model. Example usage: yarn start pong.json dqn_pong enjoy@data/dqn_cartpole_2018_12_02_124127/dqn_cartpole_t0_s0_ckptbest
• update agent load and policy to properly set variables to end_val in enjoy mode
• random-seed env as well