dead_agent

Command tracker:

python train.py --algo dqn --env gridworld

Default network architecture in policies.py -> ActorCriticPolicy (PPO) or

Name		Name	Last commit message	Last commit date
Latest commit History 23 Commits
algos		algos
graphs		graphs
minigrid_utils		minigrid_utils
modified_algos		modified_algos
optuna		optuna
optuna_utils		optuna_utils
scripts		scripts
.gitignore		.gitignore
README.md		README.md
generate_gw_script.py		generate_gw_script.py
gridworld_env.py		gridworld_env.py
minigrid.png		minigrid.png
minigrid_custom.py		minigrid_custom.py
modified_venv.py		modified_venv.py
parse_args.py		parse_args.py
play.py		play.py
requirements.txt		requirements.txt
rewards_old.json		rewards_old.json
script_test.txt		script_test.txt
test_env_speed.py		test_env_speed.py
test_run.py		test_run.py
test_traj_detection.py		test_traj_detection.py
testing_optuna.py		testing_optuna.py
testing_trials.txt		testing_trials.txt
testing_trials2.txt		testing_trials2.txt
train.py		train.py
two_wall.json		two_wall.json
utils.py		utils.py
visualize_results.ipynb		visualize_results.ipynb