Added MS Ant Walk and Run Tasks

[Xander-Hinrichsen]

MS Ant walking at 0.5 m/s and running at 4 m/s tasks

antwalk.mp4

command to run (or use example in ppo examples.sh):

for i in {1..3}; do python ppo.py --exp_name="antwalkseed${i}" --env_id="MS-AntWalk-v1" --num_envs=2048 --update_epochs=8 --num_minibatches=32 --total_timesteps=9_000_000 --eval_freq=10 --num_eval_steps=1000 --num_steps=200 --gamma=0.97 --ent_coef=1e-3 --seed=${i}; done

antrun.mp4

command to run (or use example in ppo examples.sh)::

for i in {1..3}; do python ppo.py --exp_name="antrunseed${i}" --env_id="MS-AntRun-v1" --num_envs=2048 --update_epochs=8 --num_minibatches=32 --total_timesteps=30_000_000 --eval_freq=10 --num_eval_steps=1000 --num_steps=200 --gamma=0.97 --ent_coef=1e-3 --seed=${i}; done

[StoneT2000]

@Xander-Hinrichsen any rgb results? seems quite doable given it solves in 1M steps

[Xander-Hinrichsen]

ant walk rgb

ant_walk_rgb.mp4

command (already added to ppo examples.sh):
python ppo_rgb.py --env_id="MS-AntWalk-v1"
--num_envs=256 --update_epochs=8 --num_minibatches=32
--total_timesteps=5_000_000 --eval_freq=15 --num_eval_steps=1000
--num_steps=200 --gamma=0.97 --no-include-state --render_mode="rgb_array"
--ent_coef=1e-3

ant run rgb

ant_run_rgb.mp4

command (already added to ppo examples.sh):
python ppo_rgb.py --env_id="MS-AntRun-v1"
--num_envs=256 --update_epochs=8 --num_minibatches=32
--total_timesteps=15_000_000 --eval_freq=15 --num_eval_steps=1000
--num_steps=200 --gamma=0.97 --no-include-state --render_mode="rgb_array"
--ent_coef=1e-3

edit: all evals are 33.33 seconds long, trimmed here to fit file size max on a comment