coach/benchmarks/a3c

A3C

Each experiment uses 3 seeds. The parameters used for Clipped PPO are the same parameters as described in the original paper.

Inverted Pendulum A3C - 1/2/4/8/16 workers

python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 1
python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 2
python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 4
python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 8
python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 16

Hopper A3C - 16 workers

python3 coach.py -p Mujoco_A3C -lvl hopper -n 16

Walker2D A3C - 16 workers

python3 coach.py -p Mujoco_A3C -lvl walker2d -n 16

Half Cheetah A3C - 16 workers

python3 coach.py -p Mujoco_A3C -lvl half_cheetah -n 16

Ant A3C - 16 workers

python3 coach.py -p Mujoco_A3C -lvl ant -n 16

Space Invaders A3C - 16 workers

python3 coach.py -p Atari_A3C -lvl space_invaders -n 16