Tuned examples not working

Dime · March 5, 2023, 1:12am

How severe does this issue affect your experience of using Ray?

High: It blocks me to complete my task.

Hello there,

I’ve been trying to run the tuned examples on DQN.

ray-project/ray/blob/master/rllib/tuned_examples/dqn/atari-duel-ddqn.yaml

# Runs on a single g3.4xl node
# See https://github.com/ray-project/rl-experiments for results
dueling-ddqn:
    env:
        grid_search:
            - ALE/Breakout-v5
            - ALE/BeamRider-v5
            - ALE/Qbert-v5
            - ALE/SpaceInvaders-v5
    run: DQN
    config:
        # Works for both torch and tf.
        framework: tf
        env_config:
            frameskip: 1  # no frameskip
        double_q: true
        dueling: true
        num_atoms: 1
        noisy: false
        replay_buffer_config:

This file has been truncated. show original

The only thing I’ve changed is the replay buffer size to 150k samples.

The results for Breakout aren’t anything near the scores provided by the results page.
Any pointers to what could be going wrong?

arturn · April 13, 2023, 11:45pm

Sorry for now answering this earlier. Let’s keep the discussion in Trouble reproducing results with DQN.

Topic		Replies	Views
Read Tune console output from Simple Q RLlib	8	1334	October 26, 2021
Empty checkpoint files with Tune.run RLlib	1	319	March 30, 2022
Specifying memory requirement for RLlib algorithms in Ray Tune etc RLlib	3	287	January 7, 2023
[Tune \| RLlib] Tune sample functions in yaml config files Ray Tune	6	913	October 27, 2022
How do I evaluate my trained policy after tune.fit() RLlib	1	489	March 30, 2023

Tuned examples not working

Related Topics